{ "schemaVersion": 1, "study": "004-lunar-lander", "createdAt": "2026-10-09T14:46:58.163637+00:00", "evidenceRole": "training calibration and interactive demonstration; not a benchmark claim", "runId": "ppo-train-seed-20261009-20261009T144450Z", "mode": "train", "algorithm": { "name": "PPO", "advantageEstimator": "GAE", "actor": "independent 8-64-64-4 tanh MLP", "critic": "independent 8-64-64-1 tanh MLP", "timeLimitHandling": "bootstrap V(final observation) at the 400-step truncation, then cut GAE recursion before the worker's automatic reset", "trainingObjective": "discounted continuing objective with an exogenous time limit", "evaluationHorizon": "one finite episode, capped at 400 decisions (40 seconds)", "observationNormalization": false, "rewardNormalization": false, "heuristicPretraining": false }, "rootSeed": 20261009, "hyperparameters": { "total_steps": 3145728, "num_envs": 32, "rollout_steps": 128, "update_epochs": 4, "minibatch_size": 1024, "learning_rate": 0.0003, "gamma": 0.99, "gae_lambda": 0.95, "clip_coefficient": 0.2, "value_coefficient": 0.5, "entropy_coefficient": 0.01, "max_gradient_norm": 0.5, "target_kl": 0.03, "torch_threads": 1 }, "runtime": { "python": "3.12.13", "torch": "2.13.0", "numpy": "2.5.2", "node": "v25.6.1", "planck": "1.4.2", "platform": "macOS-27.0.1-arm64-arm-64bit" }, "run": { "rootSeed": 20261009, "trainingSeeds": [ 2447455314, 1108957067, 2455024373, 3674480781, 425663664, 3093254942, 3597983459, 1331422776, 1182831386, 375285791, 3803982677, 450467216, 2186275781, 3900350102, 1738691110, 3512007463, 1274483658, 2849502796, 4293526923, 2024125041, 1021405958, 1978547863, 351617038, 4066679780, 572706809, 3641929252, 1921119264, 2483680259, 870242735, 724576387, 1088860459, 2965208912 ], "plannedTrainingSteps": 3145728, "realizedTrainingSteps": 3145728, "realizedUpdates": 768, "stopReason": "completed", "elapsedSeconds": 127.23214724997524, "checkpointFiles": { "early": ".lander-runs/ppo-train-seed-20261009-20261009T144450Z/policy-early-315392.pt", "middle": ".lander-runs/ppo-train-seed-20261009-20261009T144450Z/policy-middle-1572864.pt", "final": ".lander-runs/ppo-train-seed-20261009-20261009T144450Z/policy-final-3145728.pt" } }, "metrics": [ { "update": 1, "trainingStep": 4096, "elapsedSeconds": 0.36170824998407625, "environmentStepsPerSecond": 11324.043618524933, "learningRate": 0.0003, "loss": 331.0711193084717, "policyLoss": -0.00020490738097578287, "valueLoss": 662.1703605651855, "entropy": 1.3862797319889069, "approximateKl": 1.7584119632374495e-05, "clipFraction": 0.0, "explainedVariance": -0.0027322225881409867, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 64, "recentEpisodeCount": 64, "recentReturnMean": -108.40558614617976, "recentReturnMedian": -108.26925023138756, "recentLengthMean": 47.546875, "recentLandingRate": 0.0 }, { "update": 2, "trainingStep": 8192, "elapsedSeconds": 0.5387212909990922, "environmentStepsPerSecond": 15206.378765553198, "learningRate": 0.00029960937499999996, "loss": 420.2536029815674, "policyLoss": -0.00010367302456870675, "valueLoss": 840.5351219177246, "entropy": 1.3861828371882439, "approximateKl": 1.648079341975972e-05, "clipFraction": 0.0, "explainedVariance": -0.0026287878582118562, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 155, "recentEpisodeCount": 100, "recentReturnMean": -109.73351518400919, "recentReturnMedian": -108.83118653483689, "recentLengthMean": 48.26, "recentLandingRate": 0.0 }, { "update": 3, "trainingStep": 12288, "elapsedSeconds": 0.7098985829798039, "environmentStepsPerSecond": 17309.51475972954, "learningRate": 0.00029921875, "loss": 407.0529842376709, "policyLoss": -5.662883631885052e-05, "valueLoss": 814.1337890625, "entropy": 1.38605235517025, "approximateKl": 8.040780812734738e-06, "clipFraction": 0.0, "explainedVariance": 0.0011461474329138577, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 239, "recentEpisodeCount": 100, "recentReturnMean": -109.09177648427438, "recentReturnMedian": -108.61460097879171, "recentLengthMean": 49.4, "recentLandingRate": 0.0 }, { "update": 4, "trainingStep": 16384, "elapsedSeconds": 0.8666970409976784, "environmentStepsPerSecond": 18903.95285201382, "learningRate": 0.000298828125, "loss": 422.8561248779297, "policyLoss": -0.00014824728714302182, "valueLoss": 845.7402572631836, "entropy": 1.3859145641326904, "approximateKl": 9.978382877307013e-06, "clipFraction": 0.0, "explainedVariance": 0.0041549117696633164, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 329, "recentEpisodeCount": 100, "recentReturnMean": -108.99313402047147, "recentReturnMedian": -107.92237443337217, "recentLengthMean": 46.26, "recentLandingRate": 0.0 }, { "update": 5, "trainingStep": 20480, "elapsedSeconds": 1.0286627909808885, "environmentStepsPerSecond": 19909.34267241372, "learningRate": 0.0002984375, "loss": 408.3515224456787, "policyLoss": -0.00012462871382012963, "valueLoss": 816.7310028076172, "entropy": 1.3857565373182297, "approximateKl": 1.237160904565826e-05, "clipFraction": 0.0, "explainedVariance": 0.0033786643454085663, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 412, "recentEpisodeCount": 100, "recentReturnMean": -110.15688909541561, "recentReturnMedian": -109.1940650275792, "recentLengthMean": 47.82, "recentLandingRate": 0.0 }, { "update": 6, "trainingStep": 24576, "elapsedSeconds": 1.2006661659979727, "environmentStepsPerSecond": 20468.63707496318, "learningRate": 0.00029804687499999997, "loss": 418.9933547973633, "policyLoss": -0.00012598535977303982, "valueLoss": 838.0146751403809, "entropy": 1.3853199630975723, "approximateKl": 1.3495904568117112e-05, "clipFraction": 0.0, "explainedVariance": 0.010603492686336757, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 502, "recentEpisodeCount": 100, "recentReturnMean": -110.619356511418, "recentReturnMedian": -110.51873222738504, "recentLengthMean": 45.79, "recentLandingRate": 0.0 }, { "update": 7, "trainingStep": 28672, "elapsedSeconds": 1.3906100829772186, "environmentStepsPerSecond": 20618.28858497477, "learningRate": 0.00029765624999999996, "loss": 375.2268009185791, "policyLoss": -0.0002301200875081122, "valueLoss": 750.4817695617676, "entropy": 1.3851617872714996, "approximateKl": 1.4602377632400021e-05, "clipFraction": 0.0, "explainedVariance": 0.012856224133575789, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 583, "recentEpisodeCount": 100, "recentReturnMean": -109.70921475465788, "recentReturnMedian": -110.77966293226928, "recentLengthMean": 48.02, "recentLandingRate": 0.0 }, { "update": 8, "trainingStep": 32768, "elapsedSeconds": 1.557416124996962, "environmentStepsPerSecond": 21039.977353556627, "learningRate": 0.00029726562499999995, "loss": 384.857027053833, "policyLoss": -0.00010295480024069548, "valueLoss": 769.7419700622559, "entropy": 1.385113663971424, "approximateKl": 1.2742180842906237e-05, "clipFraction": 0.0, "explainedVariance": 0.0138822206759458, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 674, "recentEpisodeCount": 100, "recentReturnMean": -105.48074740531698, "recentReturnMedian": -103.31664233095944, "recentLengthMean": 48.53, "recentLandingRate": 0.0 }, { "update": 9, "trainingStep": 36864, "elapsedSeconds": 1.720188249979401, "environmentStepsPerSecond": 21430.212652854385, "learningRate": 0.000296875, "loss": 373.5886650085449, "policyLoss": -0.00014698246377520263, "valueLoss": 747.2053375244141, "entropy": 1.3849157318472862, "approximateKl": 7.85175507189706e-06, "clipFraction": 0.0, "explainedVariance": 0.0221059546216531, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 758, "recentEpisodeCount": 100, "recentReturnMean": -108.72171523305559, "recentReturnMedian": -108.96426306758076, "recentLengthMean": 48.2, "recentLandingRate": 0.0 }, { "update": 10, "trainingStep": 40960, "elapsedSeconds": 1.8822040829982143, "environmentStepsPerSecond": 21761.720936633872, "learningRate": 0.000296484375, "loss": 362.1276054382324, "policyLoss": -0.00011468185402918607, "valueLoss": 724.2831497192383, "entropy": 1.384672351181507, "approximateKl": 1.329640144831501e-05, "clipFraction": 0.0, "explainedVariance": 0.018247372920081495, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 836, "recentEpisodeCount": 100, "recentReturnMean": -111.52183398325433, "recentReturnMedian": -109.1888039642945, "recentLengthMean": 48.69, "recentLandingRate": 0.0 }, { "update": 11, "trainingStep": 45056, "elapsedSeconds": 2.038343749998603, "environmentStepsPerSecond": 22104.220644840145, "learningRate": 0.00029609374999999997, "loss": 358.7591857910156, "policyLoss": -0.0001422903878847137, "valueLoss": 717.5463600158691, "entropy": 1.3844200521707535, "approximateKl": 5.0869566621258855e-06, "clipFraction": 0.0, "explainedVariance": 0.020699069796878744, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 925, "recentEpisodeCount": 100, "recentReturnMean": -106.3544776467971, "recentReturnMedian": -105.85622062173206, "recentLengthMean": 48.39, "recentLandingRate": 0.01 }, { "update": 12, "trainingStep": 49152, "elapsedSeconds": 2.1944798749755137, "environmentStepsPerSecond": 22398.018118324482, "learningRate": 0.00029570312499999996, "loss": 381.7079544067383, "policyLoss": -0.0001327974023297429, "valueLoss": 763.4438896179199, "entropy": 1.3841926008462906, "approximateKl": 5.333200533641502e-06, "clipFraction": 0.0, "explainedVariance": 0.02199127075057261, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 1015, "recentEpisodeCount": 100, "recentReturnMean": -107.32676154090659, "recentReturnMedian": -105.60385143209714, "recentLengthMean": 48.48, "recentLandingRate": 0.0 }, { "update": 13, "trainingStep": 53248, "elapsedSeconds": 2.353951832978055, "environmentStepsPerSecond": 22620.68375997072, "learningRate": 0.00029531249999999995, "loss": 363.07410621643066, "policyLoss": -0.00015427381731569767, "valueLoss": 726.1762313842773, "entropy": 1.3842064216732979, "approximateKl": 6.636284524574876e-06, "clipFraction": 0.0, "explainedVariance": 0.015144302322239067, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 1099, "recentEpisodeCount": 100, "recentReturnMean": -110.07214524494542, "recentReturnMedian": -110.46560462843627, "recentLengthMean": 46.6, "recentLandingRate": 0.0 }, { "update": 14, "trainingStep": 57344, "elapsedSeconds": 2.5074153329769615, "environmentStepsPerSecond": 22869.765230285, "learningRate": 0.00029492187499999994, "loss": 350.8811855316162, "policyLoss": -0.00013031548587605357, "valueLoss": 701.790283203125, "entropy": 1.3837914913892746, "approximateKl": 7.869832188589498e-06, "clipFraction": 0.0, "explainedVariance": 0.02112185208235018, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 1182, "recentEpisodeCount": 100, "recentReturnMean": -108.94426662624261, "recentReturnMedian": -107.84779460821301, "recentLengthMean": 48.27, "recentLandingRate": 0.0 }, { "update": 15, "trainingStep": 61440, "elapsedSeconds": 2.665367207984673, "environmentStepsPerSecond": 23051.232796720633, "learningRate": 0.00029453125, "loss": 346.0117893218994, "policyLoss": -0.0001156956423074007, "valueLoss": 692.0514602661133, "entropy": 1.3832775726914406, "approximateKl": 5.880683602299541e-06, "clipFraction": 0.0, "explainedVariance": 0.0255024947152519, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 1269, "recentEpisodeCount": 100, "recentReturnMean": -109.69023671364275, "recentReturnMedian": -107.89627319481224, "recentLengthMean": 47.56, "recentLandingRate": 0.0 }, { "update": 16, "trainingStep": 65536, "elapsedSeconds": 2.815999415994156, "environmentStepsPerSecond": 23272.732099222852, "learningRate": 0.00029414062499999997, "loss": 361.11111640930176, "policyLoss": -0.00010475960152689368, "valueLoss": 722.2500953674316, "entropy": 1.3829872608184814, "approximateKl": 6.686957931378856e-06, "clipFraction": 0.0, "explainedVariance": 0.0288818757711492, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 1356, "recentEpisodeCount": 100, "recentReturnMean": -108.7921971928107, "recentReturnMedian": -110.21028495160863, "recentLengthMean": 47.11, "recentLandingRate": 0.01 }, { "update": 17, "trainingStep": 69632, "elapsedSeconds": 2.973208915995201, "environmentStepsPerSecond": 23419.814068697076, "learningRate": 0.00029374999999999996, "loss": 315.55942153930664, "policyLoss": -7.07037397660315e-05, "valueLoss": 631.1466445922852, "entropy": 1.3826778009533882, "approximateKl": 4.188608727417886e-06, "clipFraction": 0.0, "explainedVariance": 0.020939897732014212, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 1438, "recentEpisodeCount": 100, "recentReturnMean": -107.843884624333, "recentReturnMedian": -104.89688018662855, "recentLengthMean": 48.33, "recentLandingRate": 0.0 }, { "update": 18, "trainingStep": 73728, "elapsedSeconds": 3.1308744159759954, "environmentStepsPerSecond": 23548.692858386843, "learningRate": 0.000293359375, "loss": 317.2171268463135, "policyLoss": -0.00021345159620977938, "valueLoss": 634.462329864502, "entropy": 1.3827750533819199, "approximateKl": 7.409162208205089e-06, "clipFraction": 0.0, "explainedVariance": 0.01587930751040123, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 1524, "recentEpisodeCount": 100, "recentReturnMean": -106.27205591498846, "recentReturnMedian": -104.79046413023025, "recentLengthMean": 49.13, "recentLandingRate": 0.0 }, { "update": 19, "trainingStep": 77824, "elapsedSeconds": 3.28429645797587, "environmentStepsPerSecond": 23695.79025395392, "learningRate": 0.00029296875, "loss": 290.7573528289795, "policyLoss": -7.562714745290577e-05, "valueLoss": 581.5424995422363, "entropy": 1.3830029219388962, "approximateKl": 6.8784756876993924e-06, "clipFraction": 0.0, "explainedVariance": 0.018556408200372077, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 1603, "recentEpisodeCount": 100, "recentReturnMean": -106.22420084991928, "recentReturnMedian": -104.59910362638766, "recentLengthMean": 47.87, "recentLandingRate": 0.0 }, { "update": 20, "trainingStep": 81920, "elapsedSeconds": 3.4406401659944095, "environmentStepsPerSecond": 23809.52266082832, "learningRate": 0.000292578125, "loss": 336.97643280029297, "policyLoss": -9.534474520478398e-05, "valueLoss": 673.9807052612305, "entropy": 1.382898472249508, "approximateKl": 3.5583543649408966e-06, "clipFraction": 0.0, "explainedVariance": 0.01678865012004349, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 1693, "recentEpisodeCount": 100, "recentReturnMean": -106.1418153921768, "recentReturnMedian": -108.74926695402246, "recentLengthMean": 48.17, "recentLandingRate": 0.01 }, { "update": 21, "trainingStep": 86016, "elapsedSeconds": 3.594584082980873, "environmentStepsPerSecond": 23929.333134049182, "learningRate": 0.00029218749999999997, "loss": 305.23179054260254, "policyLoss": -0.00011927753803320229, "valueLoss": 610.4914741516113, "entropy": 1.3830106407403946, "approximateKl": 4.900695785181597e-06, "clipFraction": 0.0, "explainedVariance": 0.013751992798368584, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 1775, "recentEpisodeCount": 100, "recentReturnMean": -107.74214515969274, "recentReturnMedian": -104.56154806446284, "recentLengthMean": 48.78, "recentLandingRate": 0.0 }, { "update": 22, "trainingStep": 90112, "elapsedSeconds": 3.742113915999653, "environmentStepsPerSecond": 24080.506906729977, "learningRate": 0.00029179687499999996, "loss": 326.2161273956299, "policyLoss": -0.00026842067018151283, "valueLoss": 652.4604454040527, "entropy": 1.3826065957546234, "approximateKl": 1.2145828804932535e-05, "clipFraction": 0.0, "explainedVariance": 0.010354664641618716, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 1859, "recentEpisodeCount": 100, "recentReturnMean": -113.02477560388215, "recentReturnMedian": -112.76526137813926, "recentLengthMean": 50.32, "recentLandingRate": 0.0 }, { "update": 23, "trainingStep": 94208, "elapsedSeconds": 3.8906047079944983, "environmentStepsPerSecond": 24214.2307097967, "learningRate": 0.00029140624999999994, "loss": 309.6620121002197, "policyLoss": -0.00021156645379960537, "valueLoss": 619.3520851135254, "entropy": 1.3821311295032501, "approximateKl": 1.9095874449703842e-05, "clipFraction": 0.0, "explainedVariance": 0.015775701127351494, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 1944, "recentEpisodeCount": 100, "recentReturnMean": -109.73005520916894, "recentReturnMedian": -110.07013503927737, "recentLengthMean": 48.75, "recentLandingRate": 0.0 }, { "update": 24, "trainingStep": 98304, "elapsedSeconds": 4.045308749977266, "environmentStepsPerSecond": 24300.740950997235, "learningRate": 0.000291015625, "loss": 302.4823474884033, "policyLoss": -8.14537052065134e-05, "valueLoss": 604.9925079345703, "entropy": 1.3819099441170692, "approximateKl": 5.450034223031253e-06, "clipFraction": 0.0, "explainedVariance": 0.012193864713458069, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 2027, "recentEpisodeCount": 100, "recentReturnMean": -109.13845530941566, "recentReturnMedian": -107.02712397510186, "recentLengthMean": 49.87, "recentLandingRate": 0.0 }, { "update": 25, "trainingStep": 102400, "elapsedSeconds": 4.197823665977921, "environmentStepsPerSecond": 24393.592525079297, "learningRate": 0.000290625, "loss": 301.448450088501, "policyLoss": -0.00016625356511212885, "valueLoss": 602.9248886108398, "entropy": 1.3822137415409088, "approximateKl": 6.260990630835295e-06, "clipFraction": 0.0, "explainedVariance": 0.006824749007468989, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 2108, "recentEpisodeCount": 100, "recentReturnMean": -110.06688628094714, "recentReturnMedian": -110.84004027070478, "recentLengthMean": 51.19, "recentLandingRate": 0.0 }, { "update": 26, "trainingStep": 106496, "elapsedSeconds": 4.3515722079901025, "environmentStepsPerSecond": 24472.993876663306, "learningRate": 0.00029023437499999997, "loss": 283.6001396179199, "policyLoss": -0.00026976424851454794, "valueLoss": 567.2284622192383, "entropy": 1.381121352314949, "approximateKl": 1.2897959095425904e-05, "clipFraction": 0.0, "explainedVariance": 0.013425942136192748, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 2187, "recentEpisodeCount": 100, "recentReturnMean": -107.81324156394854, "recentReturnMedian": -106.81072526425123, "recentLengthMean": 48.24, "recentLandingRate": 0.0 }, { "update": 27, "trainingStep": 110592, "elapsedSeconds": 4.505596624978352, "environmentStepsPerSecond": 24545.472931796543, "learningRate": 0.00028984375, "loss": 282.3021945953369, "policyLoss": -6.318953819572926e-05, "valueLoss": 564.6321411132812, "entropy": 1.3810469806194305, "approximateKl": 8.9859968284145e-06, "clipFraction": 0.0, "explainedVariance": 0.005174583795782506, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 2270, "recentEpisodeCount": 100, "recentReturnMean": -108.04381534199081, "recentReturnMedian": -106.39742760527588, "recentLengthMean": 50.77, "recentLandingRate": 0.0 }, { "update": 28, "trainingStep": 114688, "elapsedSeconds": 4.662514540978009, "environmentStepsPerSecond": 24597.88575285452, "learningRate": 0.000289453125, "loss": 297.84169578552246, "policyLoss": -8.521502604708076e-05, "valueLoss": 595.7111511230469, "entropy": 1.3798242434859276, "approximateKl": 7.512244337704033e-06, "clipFraction": 0.0, "explainedVariance": 0.006658092264321791, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 2352, "recentEpisodeCount": 100, "recentReturnMean": -110.45253268777113, "recentReturnMedian": -108.36677549604792, "recentLengthMean": 49.21, "recentLandingRate": 0.0 }, { "update": 29, "trainingStep": 118784, "elapsedSeconds": 4.813118874997599, "environmentStepsPerSecond": 24679.21592733553, "learningRate": 0.0002890625, "loss": 274.46709156036377, "policyLoss": -9.662826778367162e-05, "valueLoss": 548.9619674682617, "entropy": 1.379249595105648, "approximateKl": 6.18462945567444e-06, "clipFraction": 0.0, "explainedVariance": 0.008077021618057456, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 2434, "recentEpisodeCount": 100, "recentReturnMean": -107.91717563205871, "recentReturnMedian": -108.0970478343661, "recentLengthMean": 48.52, "recentLandingRate": 0.0 }, { "update": 30, "trainingStep": 122880, "elapsedSeconds": 4.963883541000541, "environmentStepsPerSecond": 24754.811224928897, "learningRate": 0.000288671875, "loss": 284.5217580795288, "policyLoss": -0.00018129672389477491, "valueLoss": 569.0714664459229, "entropy": 1.379299946129322, "approximateKl": 8.984974556369707e-06, "clipFraction": 0.0, "explainedVariance": 0.010176128222911696, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 2524, "recentEpisodeCount": 100, "recentReturnMean": -107.6654424167637, "recentReturnMedian": -107.51032159850001, "recentLengthMean": 49.66, "recentLandingRate": 0.0 }, { "update": 31, "trainingStep": 126976, "elapsedSeconds": 5.116373165976256, "environmentStepsPerSecond": 24817.579930327793, "learningRate": 0.00028828124999999996, "loss": 250.1275520324707, "policyLoss": -0.00013557300553657115, "valueLoss": 500.28296661376953, "entropy": 1.3795909956097603, "approximateKl": 9.292547474615276e-06, "clipFraction": 0.0, "explainedVariance": 0.007721642318532118, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 2602, "recentEpisodeCount": 100, "recentReturnMean": -105.89787609650429, "recentReturnMedian": -102.2599313268438, "recentLengthMean": 49.58, "recentLandingRate": 0.0 }, { "update": 32, "trainingStep": 131072, "elapsedSeconds": 5.278852124989498, "environmentStepsPerSecond": 24829.640402223, "learningRate": 0.00028789062499999995, "loss": 269.7098608016968, "policyLoss": -5.518141551874578e-05, "valueLoss": 539.4474182128906, "entropy": 1.3791923522949219, "approximateKl": 1.5025267202872783e-05, "clipFraction": 0.0, "explainedVariance": 0.012350430373555765, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 2684, "recentEpisodeCount": 100, "recentReturnMean": -108.07424463307882, "recentReturnMedian": -103.94879353605211, "recentLengthMean": 49.76, "recentLandingRate": 0.0 }, { "update": 33, "trainingStep": 135168, "elapsedSeconds": 5.440244749974227, "environmentStepsPerSecond": 24845.940984666246, "learningRate": 0.0002875, "loss": 252.6050319671631, "policyLoss": -0.0002927699824795127, "valueLoss": 505.2382335662842, "entropy": 1.3799211233854294, "approximateKl": 1.9718609109986573e-05, "clipFraction": 0.0, "explainedVariance": 0.002903508129550203, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 2766, "recentEpisodeCount": 100, "recentReturnMean": -107.10622039611772, "recentReturnMedian": -105.26913361460902, "recentLengthMean": 49.64, "recentLandingRate": 0.0 }, { "update": 34, "trainingStep": 139264, "elapsedSeconds": 5.626883249991806, "environmentStepsPerSecond": 24749.758225426624, "learningRate": 0.000287109375, "loss": 252.3778018951416, "policyLoss": -0.00024830468464642763, "valueLoss": 504.78369522094727, "entropy": 1.3790552020072937, "approximateKl": 2.7968060749117285e-05, "clipFraction": 0.0, "explainedVariance": 0.007853782674833165, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 2847, "recentEpisodeCount": 100, "recentReturnMean": -107.23130782927889, "recentReturnMedian": -104.55530147021636, "recentLengthMean": 50.1, "recentLandingRate": 0.0 }, { "update": 35, "trainingStep": 143360, "elapsedSeconds": 5.935651624982711, "environmentStepsPerSecond": 24152.360862387635, "learningRate": 0.00028671874999999997, "loss": 249.6482172012329, "policyLoss": -0.00017917194054462016, "valueLoss": 499.3243656158447, "entropy": 1.3785438761115074, "approximateKl": 2.094419687637128e-05, "clipFraction": 0.0, "explainedVariance": 0.006318830465671388, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 2928, "recentEpisodeCount": 100, "recentReturnMean": -102.07161370878879, "recentReturnMedian": -102.25150403566658, "recentLengthMean": 49.97, "recentLandingRate": 0.01 }, { "update": 36, "trainingStep": 147456, "elapsedSeconds": 6.257619124982739, "environmentStepsPerSecond": 23564.23378522686, "learningRate": 0.00028632812499999996, "loss": 256.18499660491943, "policyLoss": -0.00018496112897992134, "valueLoss": 512.3979320526123, "entropy": 1.3780879974365234, "approximateKl": 6.429061613744125e-06, "clipFraction": 0.0, "explainedVariance": 0.0022431360026278213, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 3012, "recentEpisodeCount": 100, "recentReturnMean": -105.01857642201598, "recentReturnMedian": -103.68293201213237, "recentLengthMean": 50.18, "recentLandingRate": 0.0 }, { "update": 37, "trainingStep": 151552, "elapsedSeconds": 6.4355486249842215, "environmentStepsPerSecond": 23549.196631292885, "learningRate": 0.00028593749999999995, "loss": 264.7613334655762, "policyLoss": -0.00021914468379691243, "valueLoss": 529.5506725311279, "entropy": 1.3779621422290802, "approximateKl": 1.0821484465850517e-05, "clipFraction": 0.0, "explainedVariance": 0.007136964632234344, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 3097, "recentEpisodeCount": 100, "recentReturnMean": -103.73470021618043, "recentReturnMedian": -104.53248699847609, "recentLengthMean": 50.27, "recentLandingRate": 0.01 }, { "update": 38, "trainingStep": 155648, "elapsedSeconds": 6.601231665990781, "environmentStepsPerSecond": 23578.630151989786, "learningRate": 0.00028554687499999994, "loss": 236.49620819091797, "policyLoss": -0.00020746124209836125, "valueLoss": 473.0203666687012, "entropy": 1.3768936023116112, "approximateKl": 8.630300726508722e-06, "clipFraction": 0.0, "explainedVariance": 0.006043215506504107, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 3177, "recentEpisodeCount": 100, "recentReturnMean": -104.82277224747376, "recentReturnMedian": -103.49556136410683, "recentLengthMean": 49.27, "recentLandingRate": 0.0 }, { "update": 39, "trainingStep": 159744, "elapsedSeconds": 6.791690374986501, "environmentStepsPerSecond": 23520.506851774364, "learningRate": 0.00028515625, "loss": 240.8237714767456, "policyLoss": -0.00020612392108887434, "valueLoss": 481.6754856109619, "entropy": 1.376392476260662, "approximateKl": 1.641376002226025e-05, "clipFraction": 0.0, "explainedVariance": 0.00115843167039964, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 3258, "recentEpisodeCount": 100, "recentReturnMean": -105.17746237467777, "recentReturnMedian": -103.75909566273913, "recentLengthMean": 49.27, "recentLandingRate": 0.0 }, { "update": 40, "trainingStep": 163840, "elapsedSeconds": 6.97865979099879, "environmentStepsPerSecond": 23477.287173580804, "learningRate": 0.00028476562499999997, "loss": 257.52587890625, "policyLoss": -0.0004600540269166231, "valueLoss": 515.0801696777344, "entropy": 1.374947339296341, "approximateKl": 1.95348693523556e-05, "clipFraction": 0.0, "explainedVariance": 0.0005327963589086826, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 3343, "recentEpisodeCount": 100, "recentReturnMean": -108.27298248232994, "recentReturnMedian": -105.56730779958889, "recentLengthMean": 49.47, "recentLandingRate": 0.0 }, { "update": 41, "trainingStep": 167936, "elapsedSeconds": 7.1396906659938395, "environmentStepsPerSecond": 23521.467225446446, "learningRate": 0.00028437499999999996, "loss": 235.30399227142334, "policyLoss": -0.0002136899856850505, "valueLoss": 470.6359348297119, "entropy": 1.3762623071670532, "approximateKl": 3.5068685974692926e-05, "clipFraction": 0.0, "explainedVariance": 0.0036905965810707375, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 3422, "recentEpisodeCount": 100, "recentReturnMean": -107.46093352681433, "recentReturnMedian": -105.69167982088402, "recentLengthMean": 50.43, "recentLandingRate": 0.0 }, { "update": 42, "trainingStep": 172032, "elapsedSeconds": 7.300751749979099, "environmentStepsPerSecond": 23563.600830625765, "learningRate": 0.000283984375, "loss": 234.01892948150635, "policyLoss": -0.00014146510511636734, "valueLoss": 468.0656490325928, "entropy": 1.3754556700587273, "approximateKl": 9.8542841442395e-06, "clipFraction": 0.0, "explainedVariance": 0.0019171856705922918, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 3500, "recentEpisodeCount": 100, "recentReturnMean": -108.11238502592448, "recentReturnMedian": -105.05509995040484, "recentLengthMean": 51.84, "recentLandingRate": 0.0 }, { "update": 43, "trainingStep": 176128, "elapsedSeconds": 7.456058999989182, "environmentStepsPerSecond": 23622.130672551753, "learningRate": 0.00028359375, "loss": 251.3020143508911, "policyLoss": -0.00039534326060675085, "valueLoss": 502.6323013305664, "entropy": 1.3744965940713882, "approximateKl": 3.600793206715025e-05, "clipFraction": 0.0, "explainedVariance": 0.003350181362508753, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 3586, "recentEpisodeCount": 100, "recentReturnMean": -107.90680619129431, "recentReturnMedian": -106.16956717893481, "recentLengthMean": 50.66, "recentLandingRate": 0.0 }, { "update": 44, "trainingStep": 180224, "elapsedSeconds": 7.626600666000741, "environmentStepsPerSecond": 23630.97373164372, "learningRate": 0.000283203125, "loss": 237.01292037963867, "policyLoss": -4.612054908648133e-05, "valueLoss": 474.05341720581055, "entropy": 1.3740032687783241, "approximateKl": 1.5848720067879185e-05, "clipFraction": 0.0, "explainedVariance": 0.00020366540640681663, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 3665, "recentEpisodeCount": 100, "recentReturnMean": -106.84679411230317, "recentReturnMedian": -105.21142226050142, "recentLengthMean": 49.44, "recentLandingRate": 0.0 }, { "update": 45, "trainingStep": 184320, "elapsedSeconds": 7.791530749993399, "environmentStepsPerSecond": 23656.455440435264, "learningRate": 0.00028281249999999997, "loss": 226.54005813598633, "policyLoss": -0.0002743413206189871, "valueLoss": 453.10816764831543, "entropy": 1.375025361776352, "approximateKl": 1.2483767932280898e-05, "clipFraction": 0.0, "explainedVariance": 0.005952186522423242, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 3744, "recentEpisodeCount": 100, "recentReturnMean": -104.02422193527619, "recentReturnMedian": -103.83205654635094, "recentLengthMean": 52.44, "recentLandingRate": 0.01 }, { "update": 46, "trainingStep": 188416, "elapsedSeconds": 7.96271125000203, "environmentStepsPerSecond": 23662.29216210144, "learningRate": 0.00028242187499999996, "loss": 214.90815925598145, "policyLoss": -0.0002163999597541988, "valueLoss": 429.84424209594727, "entropy": 1.3745241165161133, "approximateKl": 1.7534421203890815e-05, "clipFraction": 0.0, "explainedVariance": 0.00030437985760178865, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 3818, "recentEpisodeCount": 100, "recentReturnMean": -105.04143029037382, "recentReturnMedian": -105.6322037766804, "recentLengthMean": 52.83, "recentLandingRate": 0.01 }, { "update": 47, "trainingStep": 192512, "elapsedSeconds": 8.114921707980102, "environmentStepsPerSecond": 23723.21100900904, "learningRate": 0.00028203124999999995, "loss": 216.39430141448975, "policyLoss": -0.0002325675159227103, "valueLoss": 432.81654930114746, "entropy": 1.373910829424858, "approximateKl": 1.8970706150867045e-05, "clipFraction": 0.0, "explainedVariance": 0.00453689548422942, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 3902, "recentEpisodeCount": 100, "recentReturnMean": -107.8304330128507, "recentReturnMedian": -106.3714165748097, "recentLengthMean": 52.13, "recentLandingRate": 0.0 }, { "update": 48, "trainingStep": 196608, "elapsedSeconds": 8.286456290981732, "environmentStepsPerSecond": 23726.426966611925, "learningRate": 0.000281640625, "loss": 221.20086765289307, "policyLoss": -0.000362104969099164, "valueLoss": 442.4299201965332, "entropy": 1.372955210506916, "approximateKl": 2.8499365726020187e-05, "clipFraction": 0.0, "explainedVariance": -0.0010101839316083439, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 3983, "recentEpisodeCount": 100, "recentReturnMean": -105.3675265038466, "recentReturnMedian": -102.70983999315649, "recentLengthMean": 50.63, "recentLandingRate": 0.0 }, { "update": 49, "trainingStep": 200704, "elapsedSeconds": 8.447336665994953, "environmentStepsPerSecond": 23759.44134059921, "learningRate": 0.00028125, "loss": 208.4534568786621, "policyLoss": -0.0001705220201984048, "valueLoss": 416.93471908569336, "entropy": 1.3729071617126465, "approximateKl": 2.0089148165425286e-05, "clipFraction": 0.0, "explainedVariance": 0.0030147024752732454, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 4061, "recentEpisodeCount": 100, "recentReturnMean": -105.91321735253209, "recentReturnMedian": -103.81506341509521, "recentLengthMean": 50.3, "recentLandingRate": 0.0 }, { "update": 50, "trainingStep": 204800, "elapsedSeconds": 8.604072874994017, "environmentStepsPerSecond": 23802.680774033124, "learningRate": 0.00028085937499999997, "loss": 209.00193691253662, "policyLoss": -0.00017431945889256895, "valueLoss": 418.0316867828369, "entropy": 1.3732729330658913, "approximateKl": 1.2256616173544899e-05, "clipFraction": 0.0, "explainedVariance": 0.0027914590429309882, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 4135, "recentEpisodeCount": 100, "recentReturnMean": -104.45489651081073, "recentReturnMedian": -106.0925108770025, "recentLengthMean": 52.29, "recentLandingRate": 0.01 }, { "update": 51, "trainingStep": 208896, "elapsedSeconds": 8.759678499976872, "environmentStepsPerSecond": 23847.450565742973, "learningRate": 0.00028046875, "loss": 199.2046718597412, "policyLoss": -0.0002508029283490032, "valueLoss": 398.43727111816406, "entropy": 1.3714247643947601, "approximateKl": 1.7255286365980282e-05, "clipFraction": 0.0, "explainedVariance": 0.0032329865498446075, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 4214, "recentEpisodeCount": 100, "recentReturnMean": -103.51580459922815, "recentReturnMedian": -106.523875082843, "recentLengthMean": 52.57, "recentLandingRate": 0.01 }, { "update": 52, "trainingStep": 212992, "elapsedSeconds": 8.930924415995833, "environmentStepsPerSecond": 23848.819011223328, "learningRate": 0.000280078125, "loss": 196.80161571502686, "policyLoss": -0.0003386925091035664, "valueLoss": 393.63135528564453, "entropy": 1.37241430580616, "approximateKl": 2.4996323190862313e-05, "clipFraction": 0.0, "explainedVariance": 0.0005952768651386053, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 4290, "recentEpisodeCount": 100, "recentReturnMean": -106.61256348576099, "recentReturnMedian": -107.64360352265066, "recentLengthMean": 54.14, "recentLandingRate": 0.0 }, { "update": 53, "trainingStep": 217088, "elapsedSeconds": 9.08902183297323, "environmentStepsPerSecond": 23884.638412072716, "learningRate": 0.0002796875, "loss": 204.89084911346436, "policyLoss": -0.00030205119401216507, "valueLoss": 409.8096504211426, "entropy": 1.3675631284713745, "approximateKl": 2.1482956071849912e-05, "clipFraction": 0.0, "explainedVariance": -1.139071414413273e-05, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 4369, "recentEpisodeCount": 100, "recentReturnMean": -106.3674308426155, "recentReturnMedian": -106.3402179143377, "recentLengthMean": 53.23, "recentLandingRate": 0.0 }, { "update": 54, "trainingStep": 221184, "elapsedSeconds": 9.244777165993582, "environmentStepsPerSecond": 23925.292738651777, "learningRate": 0.000279296875, "loss": 193.15383052825928, "policyLoss": -0.00048191542737185955, "valueLoss": 386.3360061645508, "entropy": 1.3689733296632767, "approximateKl": 5.070878614787944e-05, "clipFraction": 0.0, "explainedVariance": 0.0037032923211446356, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 4441, "recentEpisodeCount": 100, "recentReturnMean": -108.05582298769033, "recentReturnMedian": -106.52671911744255, "recentLengthMean": 54.35, "recentLandingRate": 0.0 }, { "update": 55, "trainingStep": 225280, "elapsedSeconds": 9.395932499988703, "environmentStepsPerSecond": 23976.332311909526, "learningRate": 0.00027890624999999997, "loss": 190.55287170410156, "policyLoss": -0.00022235591313801706, "valueLoss": 381.133508682251, "entropy": 1.366211511194706, "approximateKl": 3.584431033232249e-05, "clipFraction": 0.0, "explainedVariance": -0.0012681527900098022, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 4516, "recentEpisodeCount": 100, "recentReturnMean": -105.66688593607309, "recentReturnMedian": -103.08191043650731, "recentLengthMean": 53.32, "recentLandingRate": 0.0 }, { "update": 56, "trainingStep": 229376, "elapsedSeconds": 9.550531832996057, "environmentStepsPerSecond": 24017.091823884683, "learningRate": 0.00027851562499999995, "loss": 171.9838171005249, "policyLoss": -0.000509059929754585, "valueLoss": 343.99597358703613, "entropy": 1.3661184757947922, "approximateKl": 2.9355887818383053e-05, "clipFraction": 0.0, "explainedVariance": 0.0023743314565594087, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 4583, "recentEpisodeCount": 100, "recentReturnMean": -107.26518981324098, "recentReturnMedian": -104.53960027731955, "recentLengthMean": 55.44, "recentLandingRate": 0.0 }, { "update": 57, "trainingStep": 233472, "elapsedSeconds": 9.71114041598048, "environmentStepsPerSecond": 24041.66658076559, "learningRate": 0.000278125, "loss": 176.25835132598877, "policyLoss": -0.0003690336016006768, "valueLoss": 352.54476737976074, "entropy": 1.3663251623511314, "approximateKl": 5.043438795837574e-05, "clipFraction": 0.0, "explainedVariance": -0.003941822232292447, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 4655, "recentEpisodeCount": 100, "recentReturnMean": -107.61239263286578, "recentReturnMedian": -105.25961800431833, "recentLengthMean": 57.08, "recentLandingRate": 0.0 }, { "update": 58, "trainingStep": 237568, "elapsedSeconds": 9.866731374990195, "environmentStepsPerSecond": 24077.67992976662, "learningRate": 0.000277734375, "loss": 185.17188358306885, "policyLoss": -0.0002513909712433815, "valueLoss": 370.37158012390137, "entropy": 1.3656660690903664, "approximateKl": 1.9433147826930508e-05, "clipFraction": 0.0, "explainedVariance": -0.00011603072813759496, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 4730, "recentEpisodeCount": 100, "recentReturnMean": -105.21108101235463, "recentReturnMedian": -101.90874692046782, "recentLengthMean": 59.26, "recentLandingRate": 0.0 }, { "update": 59, "trainingStep": 241664, "elapsedSeconds": 10.026989082980435, "environmentStepsPerSecond": 24101.352659313703, "learningRate": 0.00027734375, "loss": 186.861891746521, "policyLoss": -0.00014430440205615014, "valueLoss": 373.7513313293457, "entropy": 1.3630270957946777, "approximateKl": 2.4231096176663414e-05, "clipFraction": 0.0, "explainedVariance": 0.0023315521685561835, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 4800, "recentEpisodeCount": 100, "recentReturnMean": -109.52211603829463, "recentReturnMedian": -106.44147229252849, "recentLengthMean": 57.03, "recentLandingRate": 0.0 }, { "update": 60, "trainingStep": 245760, "elapsedSeconds": 10.179587957973126, "environmentStepsPerSecond": 24142.431011415287, "learningRate": 0.00027695312499999996, "loss": 163.55052661895752, "policyLoss": -0.0006460078875534236, "valueLoss": 327.1295585632324, "entropy": 1.3607264682650566, "approximateKl": 5.0588350859470665e-05, "clipFraction": 0.0, "explainedVariance": -0.001759765941809155, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 4868, "recentEpisodeCount": 100, "recentReturnMean": -106.3612604140355, "recentReturnMedian": -103.74407463194802, "recentLengthMean": 59.13, "recentLandingRate": 0.0 }, { "update": 61, "trainingStep": 249856, "elapsedSeconds": 10.32904908299679, "environmentStepsPerSecond": 24189.642046652833, "learningRate": 0.00027656249999999995, "loss": 159.48370838165283, "policyLoss": -0.00037736192462034523, "valueLoss": 318.9954090118408, "entropy": 1.3616626039147377, "approximateKl": 4.414138675201684e-05, "clipFraction": 0.0, "explainedVariance": 0.0028310701206021305, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 4938, "recentEpisodeCount": 100, "recentReturnMean": -106.49498665372201, "recentReturnMedian": -104.81355686299503, "recentLengthMean": 58.6, "recentLandingRate": 0.0 }, { "update": 62, "trainingStep": 253952, "elapsedSeconds": 10.491584082978079, "environmentStepsPerSecond": 24205.30569945303, "learningRate": 0.00027617187499999994, "loss": 167.25732612609863, "policyLoss": -0.0005618497380055487, "valueLoss": 334.5430431365967, "entropy": 1.3632924556732178, "approximateKl": 5.5206877732416615e-05, "clipFraction": 0.0, "explainedVariance": -0.0006225788755309658, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 5012, "recentEpisodeCount": 100, "recentReturnMean": -103.94493860777467, "recentReturnMedian": -103.67412606766447, "recentLengthMean": 57.96, "recentLandingRate": 0.0 }, { "update": 63, "trainingStep": 258048, "elapsedSeconds": 10.639466458000243, "environmentStepsPerSecond": 24253.847786320464, "learningRate": 0.00027578125, "loss": 163.67813396453857, "policyLoss": -0.00025662232656031847, "valueLoss": 327.38392066955566, "entropy": 1.3571250289678574, "approximateKl": 6.223981472430751e-05, "clipFraction": 0.0, "explainedVariance": -0.0018953579147134025, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 5078, "recentEpisodeCount": 100, "recentReturnMean": -106.85062475883075, "recentReturnMedian": -105.11991902173031, "recentLengthMean": 59.49, "recentLandingRate": 0.0 }, { "update": 64, "trainingStep": 262144, "elapsedSeconds": 10.788586040987866, "environmentStepsPerSecond": 24298.272174320682, "learningRate": 0.000275390625, "loss": 169.8714199066162, "policyLoss": -0.0004327428468968719, "valueLoss": 339.77084732055664, "entropy": 1.3571701794862747, "approximateKl": 5.8198158512823284e-05, "clipFraction": 0.0, "explainedVariance": -0.0009906909427228605, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 5146, "recentEpisodeCount": 100, "recentReturnMean": -107.15819560506192, "recentReturnMedian": -106.84870300861076, "recentLengthMean": 60.12, "recentLandingRate": 0.01 }, { "update": 65, "trainingStep": 266240, "elapsedSeconds": 10.935774415993365, "environmentStepsPerSecond": 24345.783834991056, "learningRate": 0.00027499999999999996, "loss": 164.70173263549805, "policyLoss": -0.00028115769964642823, "valueLoss": 329.4311294555664, "entropy": 1.35512275993824, "approximateKl": 1.7551497876411304e-05, "clipFraction": 0.0, "explainedVariance": 0.0015180968464513223, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 5211, "recentEpisodeCount": 100, "recentReturnMean": -107.68044739664157, "recentReturnMedian": -106.96920109237544, "recentLengthMean": 62.01, "recentLandingRate": 0.01 }, { "update": 66, "trainingStep": 270336, "elapsedSeconds": 11.094491582975024, "environmentStepsPerSecond": 24366.68665510029, "learningRate": 0.000274609375, "loss": 174.56806564331055, "policyLoss": -0.0004499593342188746, "valueLoss": 349.1640739440918, "entropy": 1.3522622808814049, "approximateKl": 5.032628541812301e-05, "clipFraction": 0.0, "explainedVariance": -0.0011361928705166946, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 5280, "recentEpisodeCount": 100, "recentReturnMean": -110.56425635595915, "recentReturnMedian": -109.93474684649846, "recentLengthMean": 62.6, "recentLandingRate": 0.0 }, { "update": 67, "trainingStep": 274432, "elapsedSeconds": 11.253744624991668, "environmentStepsPerSecond": 24385.838593720815, "learningRate": 0.00027421875, "loss": 145.86559009552002, "policyLoss": -0.0004155655042268336, "valueLoss": 291.759090423584, "entropy": 1.3541428595781326, "approximateKl": 2.8921022021677345e-05, "clipFraction": 0.0, "explainedVariance": -0.0012140911487485972, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 5343, "recentEpisodeCount": 100, "recentReturnMean": -109.67176600548329, "recentReturnMedian": -107.0000056506833, "recentLengthMean": 61.56, "recentLandingRate": 0.0 }, { "update": 68, "trainingStep": 278528, "elapsedSeconds": 11.405927374988096, "environmentStepsPerSecond": 24419.583856967238, "learningRate": 0.000273828125, "loss": 169.91896533966064, "policyLoss": -0.000602951186010614, "valueLoss": 339.8661003112793, "entropy": 1.3479910045862198, "approximateKl": 6.360309271258302e-05, "clipFraction": 0.0, "explainedVariance": 0.004545001983592867, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 5415, "recentEpisodeCount": 100, "recentReturnMean": -104.12501943160024, "recentReturnMedian": -102.04602030059323, "recentLengthMean": 60.63, "recentLandingRate": 0.01 }, { "update": 69, "trainingStep": 282624, "elapsedSeconds": 11.561121874983655, "environmentStepsPerSecond": 24446.070464108794, "learningRate": 0.00027343749999999997, "loss": 157.9626522064209, "policyLoss": -0.0005840325902681798, "valueLoss": 315.9534091949463, "entropy": 1.3468415141105652, "approximateKl": 6.905199552420527e-05, "clipFraction": 0.0, "explainedVariance": -0.003464529629115587, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 5476, "recentEpisodeCount": 100, "recentReturnMean": -102.8968517623529, "recentReturnMedian": -105.49533392861485, "recentLengthMean": 63.21, "recentLandingRate": 0.02 }, { "update": 70, "trainingStep": 286720, "elapsedSeconds": 11.712133166001877, "environmentStepsPerSecond": 24480.59597138925, "learningRate": 0.00027304687499999996, "loss": 143.75049018859863, "policyLoss": -0.0007079603965394199, "valueLoss": 287.5292434692383, "entropy": 1.3422854766249657, "approximateKl": 9.031446461449377e-05, "clipFraction": 0.0, "explainedVariance": 0.003386359950479201, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 5534, "recentEpisodeCount": 100, "recentReturnMean": -100.61906875951186, "recentReturnMedian": -104.26454504969297, "recentLengthMean": 65.63, "recentLandingRate": 0.03 }, { "update": 71, "trainingStep": 290816, "elapsedSeconds": 11.860773374995915, "environmentStepsPerSecond": 24519.14312881812, "learningRate": 0.00027265624999999995, "loss": 140.6542043685913, "policyLoss": -0.0009575106669217348, "valueLoss": 281.33729362487793, "entropy": 1.3484926894307137, "approximateKl": 0.00010288324483553879, "clipFraction": 0.0, "explainedVariance": -0.0005939424406866678, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 5597, "recentEpisodeCount": 100, "recentReturnMean": -95.77422201984446, "recentReturnMedian": -100.98156747315079, "recentLengthMean": 66.15, "recentLandingRate": 0.03 }, { "update": 72, "trainingStep": 294912, "elapsedSeconds": 12.018092582991812, "environmentStepsPerSecond": 24539.002172221903, "learningRate": 0.000272265625, "loss": 118.27732563018799, "policyLoss": -0.000730993808247149, "valueLoss": 236.5828619003296, "entropy": 1.3374851867556572, "approximateKl": 0.00011857880599563941, "clipFraction": 0.0, "explainedVariance": -0.004223289828004351, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 5652, "recentEpisodeCount": 100, "recentReturnMean": -99.62357788662251, "recentReturnMedian": -100.05280553887133, "recentLengthMean": 70.56, "recentLandingRate": 0.01 }, { "update": 73, "trainingStep": 299008, "elapsedSeconds": 12.167263874987839, "environmentStepsPerSecond": 24574.793731125425, "learningRate": 0.000271875, "loss": 132.70831632614136, "policyLoss": -0.000652492803055793, "valueLoss": 265.4447650909424, "entropy": 1.3415395244956017, "approximateKl": 0.00010834844579221681, "clipFraction": 0.0, "explainedVariance": 0.0020135809161020424, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 5710, "recentEpisodeCount": 100, "recentReturnMean": -100.12762797042262, "recentReturnMedian": -101.48232469824143, "recentLengthMean": 71.9, "recentLandingRate": 0.02 }, { "update": 74, "trainingStep": 303104, "elapsedSeconds": 12.318845165980747, "environmentStepsPerSecond": 24604.903780838195, "learningRate": 0.00027148437499999997, "loss": 129.0798101425171, "policyLoss": -0.0007183481648098677, "valueLoss": 258.1878318786621, "entropy": 1.338792659342289, "approximateKl": 0.00015003143926151097, "clipFraction": 0.0, "explainedVariance": 0.003152897466681903, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 5766, "recentEpisodeCount": 100, "recentReturnMean": -93.89562757406122, "recentReturnMedian": -100.3784255888313, "recentLengthMean": 74.83, "recentLandingRate": 0.04 }, { "update": 75, "trainingStep": 307200, "elapsedSeconds": 12.473695665976265, "environmentStepsPerSecond": 24627.82548382438, "learningRate": 0.00027109375, "loss": 127.79580497741699, "policyLoss": -0.0022022381017450243, "valueLoss": 255.62259197235107, "entropy": 1.3288831412792206, "approximateKl": 0.0006081407154852059, "clipFraction": 6.103515625e-05, "explainedVariance": 0.0006288510237185685, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 5816, "recentEpisodeCount": 100, "recentReturnMean": -95.07590862345474, "recentReturnMedian": -101.14317665819544, "recentLengthMean": 75.82, "recentLandingRate": 0.04 }, { "update": 76, "trainingStep": 311296, "elapsedSeconds": 12.622913790983148, "environmentStepsPerSecond": 24661.1840304547, "learningRate": 0.000270703125, "loss": 120.79092502593994, "policyLoss": -0.0012861069408245385, "valueLoss": 241.61104106903076, "entropy": 1.330984815955162, "approximateKl": 0.0006415751340682618, "clipFraction": 0.0003662109375, "explainedVariance": 0.006296345748202814, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 5865, "recentEpisodeCount": 100, "recentReturnMean": -96.78550599469686, "recentReturnMedian": -102.49771059467457, "recentLengthMean": 75.07, "recentLandingRate": 0.04 }, { "update": 77, "trainingStep": 315392, "elapsedSeconds": 12.771907957998337, "environmentStepsPerSecond": 24694.19612458822, "learningRate": 0.0002703125, "loss": 157.67645454406738, "policyLoss": -0.0009392995270900428, "valueLoss": 315.38119316101074, "entropy": 1.3204521834850311, "approximateKl": 0.0001699695312709082, "clipFraction": 0.0, "explainedVariance": 0.0017476562665682538, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 5923, "recentEpisodeCount": 100, "recentReturnMean": -92.65341429792083, "recentReturnMedian": -101.8786572086392, "recentLengthMean": 80.38, "recentLandingRate": 0.06 }, { "update": 78, "trainingStep": 319488, "elapsedSeconds": 12.961068082979182, "environmentStepsPerSecond": 24649.820366236647, "learningRate": 0.000269921875, "loss": 132.51496696472168, "policyLoss": -0.0019427608931437135, "valueLoss": 265.0602159500122, "entropy": 1.3197077214717865, "approximateKl": 0.0009441008951398544, "clipFraction": 0.000244140625, "explainedVariance": 0.0029558788045785933, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 5974, "recentEpisodeCount": 100, "recentReturnMean": -92.18135464260318, "recentReturnMedian": -101.37059870640223, "recentLengthMean": 78.38, "recentLandingRate": 0.06 }, { "update": 79, "trainingStep": 323584, "elapsedSeconds": 13.13119433299289, "environmentStepsPerSecond": 24642.38909228358, "learningRate": 0.00026953124999999997, "loss": 110.3889889717102, "policyLoss": -0.001328531070612371, "valueLoss": 220.80696868896484, "entropy": 1.316677674651146, "approximateKl": 0.0010984467990056146, "clipFraction": 0.00067138671875, "explainedVariance": -0.005599065588938412, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 6020, "recentEpisodeCount": 100, "recentReturnMean": -90.522362388728, "recentReturnMedian": -98.43950122458045, "recentLengthMean": 83.66, "recentLandingRate": 0.05 }, { "update": 80, "trainingStep": 327680, "elapsedSeconds": 13.313618290994782, "environmentStepsPerSecond": 24612.392577128336, "learningRate": 0.00026914062499999996, "loss": 90.65474081039429, "policyLoss": -0.0005602480960078537, "valueLoss": 181.33696746826172, "entropy": 1.3182140216231346, "approximateKl": 0.00012299702211748809, "clipFraction": 0.0, "explainedVariance": -0.0012607112158884437, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 6062, "recentEpisodeCount": 100, "recentReturnMean": -90.14525854306171, "recentReturnMedian": -98.51809819997288, "recentLengthMean": 88.5, "recentLandingRate": 0.05 }, { "update": 81, "trainingStep": 331776, "elapsedSeconds": 13.474191916000564, "environmentStepsPerSecond": 24623.072171475975, "learningRate": 0.00026875, "loss": 124.73895978927612, "policyLoss": -0.001554788206703961, "valueLoss": 249.50714874267578, "entropy": 1.3060731887817383, "approximateKl": 0.001805582312954357, "clipFraction": 0.0030517578125, "explainedVariance": 0.0031841846332387735, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 6105, "recentEpisodeCount": 100, "recentReturnMean": -85.15249470778497, "recentReturnMedian": -97.55545946885832, "recentLengthMean": 93.02, "recentLandingRate": 0.07 }, { "update": 82, "trainingStep": 335872, "elapsedSeconds": 13.627887665992603, "environmentStepsPerSecond": 24645.93253422128, "learningRate": 0.000268359375, "loss": 123.28034448623657, "policyLoss": -0.002218537963926792, "valueLoss": 246.59112167358398, "entropy": 1.299707442522049, "approximateKl": 0.0012087413124390878, "clipFraction": 0.0023193359375, "explainedVariance": -0.002919658477373188, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 6144, "recentEpisodeCount": 100, "recentReturnMean": -79.12932234238298, "recentReturnMedian": -98.06528829783201, "recentLengthMean": 93.74, "recentLandingRate": 0.1 }, { "update": 83, "trainingStep": 339968, "elapsedSeconds": 13.782211374986218, "environmentStepsPerSecond": 24667.15904655322, "learningRate": 0.00026796875, "loss": 137.19542026519775, "policyLoss": -0.0035709927906282246, "valueLoss": 274.4239282608032, "entropy": 1.2974325269460678, "approximateKl": 0.004531749989837408, "clipFraction": 0.07269287109375, "explainedVariance": 0.001450950468189549, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 6180, "recentEpisodeCount": 100, "recentReturnMean": -69.54032399485281, "recentReturnMedian": -97.37421751913098, "recentLengthMean": 98.82, "recentLandingRate": 0.14 }, { "update": 84, "trainingStep": 344064, "elapsedSeconds": 13.943989915977, "environmentStepsPerSecond": 24674.716639444214, "learningRate": 0.00026757812499999997, "loss": 93.70898485183716, "policyLoss": -0.0014635275583714247, "valueLoss": 187.44652938842773, "entropy": 1.2815774604678154, "approximateKl": 0.00252402408659691, "clipFraction": 0.0159912109375, "explainedVariance": 0.00015900489302156373, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 6212, "recentEpisodeCount": 100, "recentReturnMean": -68.68559618566924, "recentReturnMedian": -95.92454284797714, "recentLengthMean": 107.38, "recentLandingRate": 0.14 }, { "update": 85, "trainingStep": 348160, "elapsedSeconds": 14.106462290976197, "environmentStepsPerSecond": 24680.886874288495, "learningRate": 0.00026718749999999996, "loss": 104.22262334823608, "policyLoss": -0.0011121646384708583, "valueLoss": 208.4733600616455, "entropy": 1.2942177057266235, "approximateKl": 0.0007233943942992482, "clipFraction": 0.0006103515625, "explainedVariance": 0.007640595526411276, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 6236, "recentEpisodeCount": 100, "recentReturnMean": -59.77488155780939, "recentReturnMedian": -95.28432558861095, "recentLengthMean": 122.36, "recentLandingRate": 0.18 }, { "update": 86, "trainingStep": 352256, "elapsedSeconds": 14.262018749985145, "environmentStepsPerSecond": 24698.887736377917, "learningRate": 0.00026679687499999994, "loss": 135.05767107009888, "policyLoss": -0.00034505381336202845, "valueLoss": 270.14193630218506, "entropy": 1.2954812198877335, "approximateKl": 9.924412370310165e-05, "clipFraction": 0.0, "explainedVariance": 0.010656836084241617, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 6269, "recentEpisodeCount": 100, "recentReturnMean": -53.26206773261147, "recentReturnMedian": -94.10131639242172, "recentLengthMean": 131.33, "recentLandingRate": 0.21 }, { "update": 87, "trainingStep": 356352, "elapsedSeconds": 14.411582499975339, "environmentStepsPerSecond": 24726.77792328565, "learningRate": 0.00026640625, "loss": 163.94140243530273, "policyLoss": -9.64801583904773e-05, "valueLoss": 327.9089756011963, "entropy": 1.2988497763872147, "approximateKl": 8.597988198744133e-06, "clipFraction": 0.0, "explainedVariance": 0.010985107986326792, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 6307, "recentEpisodeCount": 100, "recentReturnMean": -40.619005408294576, "recentReturnMedian": -91.46404329859797, "recentLengthMean": 131.91, "recentLandingRate": 0.26 }, { "update": 88, "trainingStep": 360448, "elapsedSeconds": 14.562575124989962, "environmentStepsPerSecond": 24751.66630257974, "learningRate": 0.000266015625, "loss": 158.3844108581543, "policyLoss": -0.00010996643686667085, "valueLoss": 316.79493141174316, "entropy": 1.2945083305239677, "approximateKl": 4.837787855649367e-06, "clipFraction": 0.0, "explainedVariance": 0.028533103230654167, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 6338, "recentEpisodeCount": 100, "recentReturnMean": -31.432349879410577, "recentReturnMedian": -91.41474021701288, "recentLengthMean": 127.72, "recentLandingRate": 0.3 }, { "update": 89, "trainingStep": 364544, "elapsedSeconds": 14.71480716599035, "environmentStepsPerSecond": 24773.95700043923, "learningRate": 0.00026562499999999996, "loss": 141.51935720443726, "policyLoss": -0.00034858097205869853, "valueLoss": 283.0650405883789, "entropy": 1.2815626040101051, "approximateKl": 1.5966896171448752e-05, "clipFraction": 0.0, "explainedVariance": 0.020614600134219008, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 6373, "recentEpisodeCount": 100, "recentReturnMean": -30.553207420810068, "recentReturnMedian": -89.69425377785228, "recentLengthMean": 123.02, "recentLandingRate": 0.3 }, { "update": 90, "trainingStep": 368640, "elapsedSeconds": 14.873151665990008, "environmentStepsPerSecond": 24785.60081135716, "learningRate": 0.000265234375, "loss": 164.560959815979, "policyLoss": -0.0003495186101645231, "valueLoss": 329.1479663848877, "entropy": 1.2673599869012833, "approximateKl": 2.279336331412196e-05, "clipFraction": 0.0, "explainedVariance": 0.016755913228544417, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 6409, "recentEpisodeCount": 100, "recentReturnMean": -30.593833085524455, "recentReturnMedian": -89.47905281092972, "recentLengthMean": 122.86, "recentLandingRate": 0.3 }, { "update": 91, "trainingStep": 372736, "elapsedSeconds": 15.021584124973742, "environmentStepsPerSecond": 24813.361686689055, "learningRate": 0.00026484375, "loss": 160.97715377807617, "policyLoss": -0.00022003293270245194, "valueLoss": 321.98050689697266, "entropy": 1.287985123693943, "approximateKl": 1.3081385986879468e-05, "clipFraction": 0.0, "explainedVariance": 0.03975411157123543, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 6446, "recentEpisodeCount": 100, "recentReturnMean": -35.97820157702816, "recentReturnMedian": -89.820676619187, "recentLengthMean": 114.22, "recentLandingRate": 0.27 }, { "update": 92, "trainingStep": 376832, "elapsedSeconds": 15.173378082981799, "environmentStepsPerSecond": 24835.076140536454, "learningRate": 0.000264453125, "loss": 141.92734241485596, "policyLoss": -0.00016381256864406168, "valueLoss": 283.88062381744385, "entropy": 1.28078231215477, "approximateKl": 7.038386684143916e-06, "clipFraction": 0.0, "explainedVariance": 0.08070292771397869, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 6480, "recentEpisodeCount": 100, "recentReturnMean": -36.11377898055151, "recentReturnMedian": -90.19693296938203, "recentLengthMean": 115.1, "recentLandingRate": 0.27 }, { "update": 93, "trainingStep": 380928, "elapsedSeconds": 15.32395995798288, "environmentStepsPerSecond": 24858.326505973346, "learningRate": 0.0002640625, "loss": 158.80452060699463, "policyLoss": -0.00012646507821045816, "valueLoss": 317.6350746154785, "entropy": 1.2890149280428886, "approximateKl": 8.216156857088208e-06, "clipFraction": 0.0, "explainedVariance": 0.12154055535187391, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 6509, "recentEpisodeCount": 100, "recentReturnMean": -25.294869637749215, "recentReturnMedian": -89.62430953700095, "recentLengthMean": 116.77, "recentLandingRate": 0.32 }, { "update": 94, "trainingStep": 385024, "elapsedSeconds": 15.473967624973739, "environmentStepsPerSecond": 24882.047664272108, "learningRate": 0.00026367187499999996, "loss": 152.96937036514282, "policyLoss": -0.0004139055381529033, "valueLoss": 305.96508026123047, "entropy": 1.2754368409514427, "approximateKl": 5.653341577271931e-05, "clipFraction": 0.0, "explainedVariance": 0.07416304992251521, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 6546, "recentEpisodeCount": 100, "recentReturnMean": -27.284623777584056, "recentReturnMedian": -89.90908839250915, "recentLengthMean": 124.19, "recentLandingRate": 0.31 }, { "update": 95, "trainingStep": 389120, "elapsedSeconds": 15.6199561249814, "environmentStepsPerSecond": 24911.721703089188, "learningRate": 0.00026328124999999995, "loss": 163.77563381195068, "policyLoss": -0.0005556601972784847, "valueLoss": 327.577844619751, "entropy": 1.273285634815693, "approximateKl": 5.625435369438492e-05, "clipFraction": 0.0, "explainedVariance": 0.06879805388460991, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 6581, "recentEpisodeCount": 100, "recentReturnMean": -21.958576993710594, "recentReturnMedian": -88.85587835591286, "recentLengthMean": 120.71, "recentLandingRate": 0.33 }, { "update": 96, "trainingStep": 393216, "elapsedSeconds": 15.767728082981193, "environmentStepsPerSecond": 24938.025182233796, "learningRate": 0.000262890625, "loss": 164.5490550994873, "policyLoss": -0.00023898447398096323, "valueLoss": 329.12403869628906, "entropy": 1.272546835243702, "approximateKl": 2.4972716346383095e-05, "clipFraction": 0.0, "explainedVariance": 0.13365549042461777, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 6613, "recentEpisodeCount": 100, "recentReturnMean": -20.170268089009916, "recentReturnMedian": -88.64621821127366, "recentLengthMean": 121.36, "recentLandingRate": 0.34 }, { "update": 97, "trainingStep": 397312, "elapsedSeconds": 15.926720749994274, "environmentStepsPerSecond": 24946.252667872188, "learningRate": 0.0002625, "loss": 172.43340682983398, "policyLoss": -0.00024061781005002558, "valueLoss": 344.89257049560547, "entropy": 1.2633680775761604, "approximateKl": 6.878817657707259e-06, "clipFraction": 0.0, "explainedVariance": 0.13928734504313656, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 6645, "recentEpisodeCount": 100, "recentReturnMean": -7.549626481317827, "recentReturnMedian": -88.23374670214253, "recentLengthMean": 116.44, "recentLandingRate": 0.4 }, { "update": 98, "trainingStep": 401408, "elapsedSeconds": 16.07845841598464, "environmentStepsPerSecond": 24965.577520848277, "learningRate": 0.00026210937499999997, "loss": 146.36206245422363, "policyLoss": -0.0004060267237946391, "valueLoss": 292.75016021728516, "entropy": 1.2613475248217583, "approximateKl": 4.340015220805071e-05, "clipFraction": 0.0, "explainedVariance": 0.04907807241143691, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 6678, "recentEpisodeCount": 100, "recentReturnMean": -14.638800526342093, "recentReturnMedian": -88.30647159484215, "recentLengthMean": 121.71, "recentLandingRate": 0.37 }, { "update": 99, "trainingStep": 405504, "elapsedSeconds": 16.234229290974326, "environmentStepsPerSecond": 24978.33390991011, "learningRate": 0.00026171874999999996, "loss": 146.27902030944824, "policyLoss": -0.00033805600833147764, "valueLoss": 292.5838851928711, "entropy": 1.2583831325173378, "approximateKl": 5.3469302656594664e-05, "clipFraction": 0.0, "explainedVariance": 0.1605455411585366, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 6703, "recentEpisodeCount": 100, "recentReturnMean": -3.224816561401676, "recentReturnMedian": -87.17420507362112, "recentLengthMean": 131.39, "recentLandingRate": 0.42 }, { "update": 100, "trainingStep": 409600, "elapsedSeconds": 16.38332624998293, "environmentStepsPerSecond": 25001.028103217246, "learningRate": 0.00026132812499999995, "loss": 157.23248672485352, "policyLoss": -0.00020118651445955038, "valueLoss": 314.4908332824707, "entropy": 1.2729241624474525, "approximateKl": 2.27753771468997e-05, "clipFraction": 0.0, "explainedVariance": 0.10819224517202264, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 6735, "recentEpisodeCount": 100, "recentReturnMean": -9.776490089624277, "recentReturnMedian": -88.66451699679601, "recentLengthMean": 135.03, "recentLandingRate": 0.39 }, { "update": 101, "trainingStep": 413696, "elapsedSeconds": 16.529760499979602, "environmentStepsPerSecond": 25027.34386263555, "learningRate": 0.00026093749999999994, "loss": 144.04827308654785, "policyLoss": -0.0001794822746887803, "valueLoss": 288.12220573425293, "entropy": 1.2649803385138512, "approximateKl": 7.441748311975971e-05, "clipFraction": 0.0, "explainedVariance": 0.12318012786279464, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 6763, "recentEpisodeCount": 100, "recentReturnMean": -1.2410954957056675, "recentReturnMedian": -86.69718855914834, "recentLengthMean": 139.5, "recentLandingRate": 0.43 }, { "update": 102, "trainingStep": 417792, "elapsedSeconds": 16.683918999973685, "environmentStepsPerSecond": 25041.598439830534, "learningRate": 0.000260546875, "loss": 140.60083293914795, "policyLoss": -0.00024415526422671974, "valueLoss": 281.22747230529785, "entropy": 1.2655036970973015, "approximateKl": 2.195752676925622e-05, "clipFraction": 0.0, "explainedVariance": 0.18699997670501123, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 6790, "recentEpisodeCount": 100, "recentReturnMean": -4.5899908171084824, "recentReturnMedian": -88.0033530537039, "recentLengthMean": 137.45, "recentLandingRate": 0.42 }, { "update": 103, "trainingStep": 421888, "elapsedSeconds": 16.834648666001158, "environmentStepsPerSecond": 25060.695258347423, "learningRate": 0.00026015624999999997, "loss": 126.36818170547485, "policyLoss": -0.0008914953214116395, "valueLoss": 252.7634983062744, "entropy": 1.267640009522438, "approximateKl": 0.00010987244968418963, "clipFraction": 0.0, "explainedVariance": 0.07363090644772585, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 6817, "recentEpisodeCount": 100, "recentReturnMean": -17.437617350167855, "recentReturnMedian": -89.82635030150414, "recentLengthMean": 142.13, "recentLandingRate": 0.36 }, { "update": 104, "trainingStep": 425984, "elapsedSeconds": 16.989743040991016, "environmentStepsPerSecond": 25073.01016691258, "learningRate": 0.00025976562499999996, "loss": 170.62316226959229, "policyLoss": -0.0002672540722414851, "valueLoss": 341.2721481323242, "entropy": 1.2645358443260193, "approximateKl": 0.00012862521907663904, "clipFraction": 0.0, "explainedVariance": 0.1264855910971605, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 6848, "recentEpisodeCount": 100, "recentReturnMean": -4.764440230636828, "recentReturnMedian": -87.51979597378522, "recentLengthMean": 147.25, "recentLandingRate": 0.42 }, { "update": 105, "trainingStep": 430080, "elapsedSeconds": 17.135557000001427, "environmentStepsPerSecond": 25098.688067155574, "learningRate": 0.000259375, "loss": 124.47398376464844, "policyLoss": -0.00013357086572796106, "valueLoss": 248.97358322143555, "entropy": 1.267480231821537, "approximateKl": 8.732498827157542e-06, "clipFraction": 0.0, "explainedVariance": -0.011303015033303554, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 6874, "recentEpisodeCount": 100, "recentReturnMean": -10.175088291150168, "recentReturnMedian": -89.07449502852978, "recentLengthMean": 151.71, "recentLandingRate": 0.39 }, { "update": 106, "trainingStep": 434176, "elapsedSeconds": 17.29346624997561, "environmentStepsPerSecond": 25106.360617589453, "learningRate": 0.000258984375, "loss": 150.83205032348633, "policyLoss": -0.000252576544880867, "valueLoss": 301.68996810913086, "entropy": 1.2681831866502762, "approximateKl": 3.161225686199032e-05, "clipFraction": 0.0, "explainedVariance": 0.09012973079657327, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 6902, "recentEpisodeCount": 100, "recentReturnMean": -11.460709817015449, "recentReturnMedian": -89.30641124083195, "recentLengthMean": 148.99, "recentLandingRate": 0.39 }, { "update": 107, "trainingStep": 438272, "elapsedSeconds": 17.45867562497733, "environmentStepsPerSecond": 25103.393259279313, "learningRate": 0.00025859375, "loss": 124.65946054458618, "policyLoss": -0.000341540842782706, "valueLoss": 249.34518814086914, "entropy": 1.2790661379694939, "approximateKl": 2.5723860744619742e-05, "clipFraction": 0.0, "explainedVariance": 0.06555818147172676, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 6927, "recentEpisodeCount": 100, "recentReturnMean": -9.331541370015147, "recentReturnMedian": -88.8581667219405, "recentLengthMean": 149.12, "recentLandingRate": 0.4 }, { "update": 108, "trainingStep": 442368, "elapsedSeconds": 17.61441024998203, "environmentStepsPerSecond": 25113.98302423729, "learningRate": 0.00025820312499999997, "loss": 107.39572763442993, "policyLoss": -0.0007543798419646919, "valueLoss": 214.81833267211914, "entropy": 1.2685067430138588, "approximateKl": 0.00016910077101783827, "clipFraction": 0.0, "explainedVariance": 0.08719877725687442, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 6950, "recentEpisodeCount": 100, "recentReturnMean": -20.904877174163374, "recentReturnMedian": -91.26233108760789, "recentLengthMean": 152.95, "recentLandingRate": 0.35 }, { "update": 109, "trainingStep": 446464, "elapsedSeconds": 17.762642415997107, "environmentStepsPerSecond": 25134.999035836736, "learningRate": 0.00025781249999999996, "loss": 125.49365329742432, "policyLoss": -0.0007007851381786168, "valueLoss": 251.01397037506104, "entropy": 1.2631918638944626, "approximateKl": 0.0002773232408799231, "clipFraction": 0.0, "explainedVariance": 0.07911689191869065, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 6974, "recentEpisodeCount": 100, "recentReturnMean": -14.040473038689342, "recentReturnMedian": -89.14668066590093, "recentLengthMean": 162.12, "recentLandingRate": 0.39 }, { "update": 110, "trainingStep": 450560, "elapsedSeconds": 17.909041040984448, "environmentStepsPerSecond": 25158.24264230024, "learningRate": 0.00025742187499999995, "loss": 106.28114461898804, "policyLoss": -0.00022238750534597784, "valueLoss": 212.58802700042725, "entropy": 1.264680027961731, "approximateKl": 0.0001379084715154022, "clipFraction": 0.0, "explainedVariance": 0.04643689564788411, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 6994, "recentEpisodeCount": 100, "recentReturnMean": -8.808956379300325, "recentReturnMedian": -87.761445942102, "recentLengthMean": 168.09, "recentLandingRate": 0.41 }, { "update": 111, "trainingStep": 454656, "elapsedSeconds": 18.05426241600071, "environmentStepsPerSecond": 25182.751281883335, "learningRate": 0.00025703125, "loss": 117.0687837600708, "policyLoss": -0.00032653467496857047, "valueLoss": 234.1635389328003, "entropy": 1.2658745646476746, "approximateKl": 6.811022467445582e-05, "clipFraction": 0.0, "explainedVariance": 0.13977149937279842, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 7018, "recentEpisodeCount": 100, "recentReturnMean": -10.394456439742752, "recentReturnMedian": -89.14668066590093, "recentLengthMean": 178.36, "recentLandingRate": 0.41 }, { "update": 112, "trainingStep": 458752, "elapsedSeconds": 18.197278124978766, "environmentStepsPerSecond": 25209.92408036492, "learningRate": 0.000256640625, "loss": 68.09152412414551, "policyLoss": -0.0006705440173391253, "valueLoss": 136.20978546142578, "entropy": 1.2697719857096672, "approximateKl": 0.00039534398820251226, "clipFraction": 0.0, "explainedVariance": 0.0827260522170623, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 7034, "recentEpisodeCount": 100, "recentReturnMean": -12.774602426415113, "recentReturnMedian": -91.54741932987235, "recentLengthMean": 184.21, "recentLandingRate": 0.4 }, { "update": 113, "trainingStep": 462848, "elapsedSeconds": 18.353189999994356, "environmentStepsPerSecond": 25218.940140659055, "learningRate": 0.00025624999999999997, "loss": 108.1553635597229, "policyLoss": -0.00046179938362911344, "valueLoss": 216.33677291870117, "entropy": 1.25599505007267, "approximateKl": 0.0003659565336420201, "clipFraction": 0.0, "explainedVariance": 0.015266109063238664, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 7056, "recentEpisodeCount": 100, "recentReturnMean": -16.113218035575663, "recentReturnMedian": -93.53834661724977, "recentLengthMean": 192.87, "recentLandingRate": 0.39 }, { "update": 114, "trainingStep": 466944, "elapsedSeconds": 18.504892749973806, "environmentStepsPerSecond": 25233.54262621495, "learningRate": 0.000255859375, "loss": 125.75906419754028, "policyLoss": -0.000165474513778463, "valueLoss": 251.54370307922363, "entropy": 1.2621717974543571, "approximateKl": 1.87492769327946e-05, "clipFraction": 0.0, "explainedVariance": 0.05743266301182748, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 7082, "recentEpisodeCount": 100, "recentReturnMean": -19.953462931116775, "recentReturnMedian": -93.53834661724977, "recentLengthMean": 189.24, "recentLandingRate": 0.37 }, { "update": 115, "trainingStep": 471040, "elapsedSeconds": 18.656036665983265, "environmentStepsPerSecond": 25248.663927578848, "learningRate": 0.00025546875, "loss": 97.32646608352661, "policyLoss": -0.00020598687115125358, "valueLoss": 194.6785707473755, "entropy": 1.261294923722744, "approximateKl": 6.46305525151547e-05, "clipFraction": 0.0, "explainedVariance": 0.1445187227526601, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 7101, "recentEpisodeCount": 100, "recentReturnMean": -21.21118593302668, "recentReturnMedian": -92.85414243931882, "recentLengthMean": 185.97, "recentLandingRate": 0.36 }, { "update": 116, "trainingStep": 475136, "elapsedSeconds": 18.817669749987544, "environmentStepsPerSecond": 25249.460018837588, "learningRate": 0.000255078125, "loss": 95.0382719039917, "policyLoss": -0.0004809125675819814, "valueLoss": 190.10266304016113, "entropy": 1.2579372748732567, "approximateKl": 0.00014442404790315777, "clipFraction": 0.0, "explainedVariance": 0.10163129279610039, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 7122, "recentEpisodeCount": 100, "recentReturnMean": -25.384281807794142, "recentReturnMedian": -92.52615259448066, "recentLengthMean": 188.47, "recentLandingRate": 0.34 }, { "update": 117, "trainingStep": 479232, "elapsedSeconds": 18.993392374977702, "environmentStepsPerSecond": 25231.511598283538, "learningRate": 0.0002546875, "loss": 114.3182487487793, "policyLoss": -0.00030522432643920183, "valueLoss": 228.66243934631348, "entropy": 1.2666392102837563, "approximateKl": 4.5046985178487375e-05, "clipFraction": 0.0, "explainedVariance": 0.08842082692393927, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 7145, "recentEpisodeCount": 100, "recentReturnMean": -15.989482939965091, "recentReturnMedian": -89.1642609401606, "recentLengthMean": 190.35, "recentLandingRate": 0.38 }, { "update": 118, "trainingStep": 483328, "elapsedSeconds": 19.14736574998824, "environmentStepsPerSecond": 25242.53238335393, "learningRate": 0.00025429687499999997, "loss": 124.22747564315796, "policyLoss": -0.0003466092166490853, "valueLoss": 248.4806890487671, "entropy": 1.2521295323967934, "approximateKl": 0.0002580683649284765, "clipFraction": 0.0, "explainedVariance": 0.15029367300487428, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 7170, "recentEpisodeCount": 100, "recentReturnMean": -11.988321863304009, "recentReturnMedian": -88.79391572368331, "recentLengthMean": 182.0, "recentLandingRate": 0.4 }, { "update": 119, "trainingStep": 487424, "elapsedSeconds": 19.29424074999406, "environmentStepsPerSecond": 25262.668084005847, "learningRate": 0.00025390624999999995, "loss": 109.00965738296509, "policyLoss": -0.00026463478570804, "valueLoss": 218.04499435424805, "entropy": 1.2574622258543968, "approximateKl": 0.00016446348672616296, "clipFraction": 0.0, "explainedVariance": 0.11185928707931936, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 7192, "recentEpisodeCount": 100, "recentReturnMean": -6.134884416980494, "recentReturnMedian": -87.55218613892794, "recentLengthMean": 184.98, "recentLandingRate": 0.43 }, { "update": 120, "trainingStep": 491520, "elapsedSeconds": 19.440543082979275, "environmentStepsPerSecond": 25283.24429528613, "learningRate": 0.000253515625, "loss": 105.52038955688477, "policyLoss": -0.0006562258931808174, "valueLoss": 211.06716918945312, "entropy": 1.2539525255560875, "approximateKl": 0.00017476990615250543, "clipFraction": 0.0, "explainedVariance": 0.14143436154530087, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 7212, "recentEpisodeCount": 100, "recentReturnMean": 2.608307809277176, "recentReturnMedian": -85.82928848505253, "recentLengthMean": 184.82, "recentLandingRate": 0.47 }, { "update": 121, "trainingStep": 495616, "elapsedSeconds": 19.58818991598673, "environmentStepsPerSecond": 25301.776331845103, "learningRate": 0.000253125, "loss": 89.33620929718018, "policyLoss": -0.00044013926526531577, "valueLoss": 178.69855880737305, "entropy": 1.2629891484975815, "approximateKl": 0.00014231597378966399, "clipFraction": 0.0, "explainedVariance": 0.0852109760709594, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 7230, "recentEpisodeCount": 100, "recentReturnMean": 12.740949013323844, "recentReturnMedian": 99.68422928272048, "recentLengthMean": 191.6, "recentLandingRate": 0.52 }, { "update": 122, "trainingStep": 499712, "elapsedSeconds": 19.737838207976893, "environmentStepsPerSecond": 25317.46358109498, "learningRate": 0.000252734375, "loss": 130.92700815200806, "policyLoss": -0.00010017445310950279, "valueLoss": 261.87944316864014, "entropy": 1.2614381834864616, "approximateKl": 0.0001651298334763851, "clipFraction": 0.0, "explainedVariance": 0.12209007060153199, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 7256, "recentEpisodeCount": 100, "recentReturnMean": 16.392102735614024, "recentReturnMedian": 100.5511537946295, "recentLengthMean": 189.19, "recentLandingRate": 0.54 }, { "update": 123, "trainingStep": 503808, "elapsedSeconds": 20.05828595798812, "environmentStepsPerSecond": 25117.200993904506, "learningRate": 0.00025234374999999996, "loss": 100.46911239624023, "policyLoss": -0.0008850080776028335, "valueLoss": 200.96519565582275, "entropy": 1.259955756366253, "approximateKl": 0.0003471538620942738, "clipFraction": 0.0, "explainedVariance": 0.06153622154768745, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 7277, "recentEpisodeCount": 100, "recentReturnMean": 13.273916967264718, "recentReturnMedian": 97.53719934402034, "recentLengthMean": 190.49, "recentLandingRate": 0.52 }, { "update": 124, "trainingStep": 507904, "elapsedSeconds": 20.21205612499034, "environmentStepsPerSecond": 25128.764577890895, "learningRate": 0.00025195312499999995, "loss": 163.18843936920166, "policyLoss": -0.0006326379952952266, "valueLoss": 326.4032402038574, "entropy": 1.2546942383050919, "approximateKl": 0.00030116217021713965, "clipFraction": 0.0, "explainedVariance": 0.1141489727912608, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 7309, "recentEpisodeCount": 100, "recentReturnMean": 12.902275903658788, "recentReturnMedian": 94.67147587635554, "recentLengthMean": 182.09, "recentLandingRate": 0.51 }, { "update": 125, "trainingStep": 512000, "elapsedSeconds": 20.35964533299557, "environmentStepsPerSecond": 25147.7858099146, "learningRate": 0.00025156249999999994, "loss": 129.91017293930054, "policyLoss": -0.00029886135598644614, "valueLoss": 259.8461561203003, "entropy": 1.2606658041477203, "approximateKl": 9.897048585116863e-05, "clipFraction": 0.0, "explainedVariance": 0.11743321636536763, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 7333, "recentEpisodeCount": 100, "recentReturnMean": 15.885726701151775, "recentReturnMedian": 101.4593849463854, "recentLengthMean": 169.95, "recentLandingRate": 0.52 }, { "update": 126, "trainingStep": 516096, "elapsedSeconds": 20.50900016599917, "environmentStepsPerSecond": 25164.366659648742, "learningRate": 0.000251171875, "loss": 156.6627540588379, "policyLoss": -0.0002708076499402523, "valueLoss": 313.35120964050293, "entropy": 1.2582347989082336, "approximateKl": 7.441837442456745e-05, "clipFraction": 0.0, "explainedVariance": 0.10460128416607228, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 7364, "recentEpisodeCount": 100, "recentReturnMean": 16.21473468662896, "recentReturnMedian": 106.62810825600172, "recentLengthMean": 161.29, "recentLandingRate": 0.52 }, { "update": 127, "trainingStep": 520192, "elapsedSeconds": 20.657974290981656, "environmentStepsPerSecond": 25181.17181640082, "learningRate": 0.00025078125, "loss": 153.00533771514893, "policyLoss": -0.0005239274178165942, "valueLoss": 306.03672218322754, "entropy": 1.2500225827097893, "approximateKl": 0.00017467982252128422, "clipFraction": 6.103515625e-05, "explainedVariance": 0.08571756021727706, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 7393, "recentEpisodeCount": 100, "recentReturnMean": 19.485698694231267, "recentReturnMedian": 110.44570582266897, "recentLengthMean": 147.99, "recentLandingRate": 0.53 }, { "update": 128, "trainingStep": 524288, "elapsedSeconds": 20.809556207997957, "environmentStepsPerSecond": 25194.5786233776, "learningRate": 0.00025039062499999996, "loss": 157.6648759841919, "policyLoss": -6.335455691441894e-05, "valueLoss": 315.35494232177734, "entropy": 1.2531432807445526, "approximateKl": 0.00012371704724500887, "clipFraction": 0.0, "explainedVariance": 0.07739610829290244, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 7423, "recentEpisodeCount": 100, "recentReturnMean": 17.791807677051928, "recentReturnMedian": 108.20302468698355, "recentLengthMean": 143.0, "recentLandingRate": 0.52 }, { "update": 129, "trainingStep": 528384, "elapsedSeconds": 20.963854000001447, "environmentStepsPerSecond": 25204.525847201738, "learningRate": 0.00025, "loss": 164.10960006713867, "policyLoss": -0.00019173903274349868, "valueLoss": 328.2445240020752, "entropy": 1.2469962015748024, "approximateKl": 9.162687638308853e-05, "clipFraction": 0.0, "explainedVariance": 0.12666308729368425, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 7456, "recentEpisodeCount": 100, "recentReturnMean": 18.852741960064087, "recentReturnMedian": 112.88388451840729, "recentLengthMean": 133.33, "recentLandingRate": 0.52 }, { "update": 130, "trainingStep": 532480, "elapsedSeconds": 21.116060915985145, "environmentStepsPerSecond": 25216.824393459927, "learningRate": 0.000249609375, "loss": 134.14183568954468, "policyLoss": -0.00070713329478167, "valueLoss": 268.31020069122314, "entropy": 1.255955420434475, "approximateKl": 0.0003177910220983904, "clipFraction": 0.0, "explainedVariance": 0.1282209782470347, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 7484, "recentEpisodeCount": 100, "recentReturnMean": 27.395877759117067, "recentReturnMedian": 116.42877115617739, "recentLengthMean": 127.59, "recentLandingRate": 0.56 }, { "update": 131, "trainingStep": 536576, "elapsedSeconds": 21.283691958000418, "environmentStepsPerSecond": 25210.663688369354, "learningRate": 0.00024921875, "loss": 157.84247493743896, "policyLoss": -4.302815068513155e-05, "valueLoss": 315.7099952697754, "entropy": 1.247695468366146, "approximateKl": 0.00015411212370963767, "clipFraction": 0.0, "explainedVariance": 0.16594075427183286, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 7519, "recentEpisodeCount": 100, "recentReturnMean": 37.773677787682864, "recentReturnMedian": 116.99050429662748, "recentLengthMean": 128.58, "recentLandingRate": 0.61 }, { "update": 132, "trainingStep": 540672, "elapsedSeconds": 21.452267832995858, "environmentStepsPerSecond": 25203.489169960354, "learningRate": 0.00024882812499999997, "loss": 195.63504028320312, "policyLoss": -0.000645192718366161, "valueLoss": 391.2964286804199, "entropy": 1.2529701814055443, "approximateKl": 0.00021607874077744782, "clipFraction": 0.0, "explainedVariance": 0.09679288017750953, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 7557, "recentEpisodeCount": 100, "recentReturnMean": 33.97215940871127, "recentReturnMedian": 117.85286985361017, "recentLengthMean": 120.68, "recentLandingRate": 0.59 }, { "update": 133, "trainingStep": 544768, "elapsedSeconds": 21.616213999979664, "environmentStepsPerSecond": 25201.82303897031, "learningRate": 0.00024843749999999996, "loss": 206.37400722503662, "policyLoss": -0.00018158229067921638, "valueLoss": 412.77330017089844, "entropy": 1.2460252568125725, "approximateKl": 0.00026249389338772744, "clipFraction": 0.0, "explainedVariance": 0.11660210935859394, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 7600, "recentEpisodeCount": 100, "recentReturnMean": 28.31444508506971, "recentReturnMedian": 118.21618090104312, "recentLengthMean": 114.29, "recentLandingRate": 0.56 }, { "update": 134, "trainingStep": 548864, "elapsedSeconds": 21.78104095798335, "environmentStepsPerSecond": 25199.162935269458, "learningRate": 0.00024804687499999995, "loss": 198.2929401397705, "policyLoss": -0.0006700519588775933, "valueLoss": 396.612211227417, "entropy": 1.249424047768116, "approximateKl": 0.00015502621681662276, "clipFraction": 0.0, "explainedVariance": 0.12343271242265075, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 7641, "recentEpisodeCount": 100, "recentReturnMean": 20.574374428868104, "recentReturnMedian": 114.3515216880478, "recentLengthMean": 106.9, "recentLandingRate": 0.52 }, { "update": 135, "trainingStep": 552960, "elapsedSeconds": 21.9398241659801, "environmentStepsPerSecond": 25203.483665900112, "learningRate": 0.00024765625, "loss": 171.65375900268555, "policyLoss": -7.501820800825953e-05, "valueLoss": 343.3324680328369, "entropy": 1.239906445145607, "approximateKl": 8.054492718656547e-05, "clipFraction": 0.0, "explainedVariance": 0.07199523116531803, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 7674, "recentEpisodeCount": 100, "recentReturnMean": 23.658534938183656, "recentReturnMedian": 118.51627743500285, "recentLengthMean": 103.73, "recentLandingRate": 0.53 }, { "update": 136, "trainingStep": 557056, "elapsedSeconds": 22.094480915984605, "environmentStepsPerSecond": 25212.450209544815, "learningRate": 0.000247265625, "loss": 170.12678623199463, "policyLoss": -0.0007093078165780753, "valueLoss": 340.2799530029297, "entropy": 1.248344324529171, "approximateKl": 0.00023314908321481198, "clipFraction": 0.0, "explainedVariance": 0.09329358702782542, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 7711, "recentEpisodeCount": 100, "recentReturnMean": 29.778762827620014, "recentReturnMedian": 118.29566671699286, "recentLengthMean": 104.91, "recentLandingRate": 0.56 }, { "update": 137, "trainingStep": 561152, "elapsedSeconds": 22.25083987499238, "environmentStepsPerSecond": 25219.362646651207, "learningRate": 0.00024687499999999997, "loss": 198.62752056121826, "policyLoss": -0.0008643106702947989, "valueLoss": 397.2815399169922, "entropy": 1.238282322883606, "approximateKl": 0.0006763707933714613, "clipFraction": 0.0, "explainedVariance": 0.11048033644977906, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 7750, "recentEpisodeCount": 100, "recentReturnMean": 26.897793177920175, "recentReturnMedian": 116.03795508365147, "recentLengthMean": 109.62, "recentLandingRate": 0.55 }, { "update": 138, "trainingStep": 565248, "elapsedSeconds": 22.401910665998003, "environmentStepsPerSecond": 25232.133474130085, "learningRate": 0.000246484375, "loss": 165.24363708496094, "policyLoss": -0.0005713091813959181, "valueLoss": 330.51323318481445, "entropy": 1.2411911189556122, "approximateKl": 0.0003694423103297595, "clipFraction": 0.0, "explainedVariance": 0.11779824693910779, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 7785, "recentEpisodeCount": 100, "recentReturnMean": 28.942902744746387, "recentReturnMedian": 116.30737176374532, "recentLengthMean": 111.42, "recentLandingRate": 0.56 }, { "update": 139, "trainingStep": 569344, "elapsedSeconds": 22.554401874978794, "environmentStepsPerSecond": 25243.143363141626, "learningRate": 0.00024609375, "loss": 172.04011154174805, "policyLoss": -0.00017847638810053468, "valueLoss": 344.10558319091797, "entropy": 1.2499012500047684, "approximateKl": 7.174124766606838e-05, "clipFraction": 0.0, "explainedVariance": 0.09210479526950366, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 7819, "recentEpisodeCount": 100, "recentReturnMean": 24.674094607326914, "recentReturnMedian": 115.8225123216398, "recentLengthMean": 111.87, "recentLandingRate": 0.54 }, { "update": 140, "trainingStep": 573440, "elapsedSeconds": 22.70507145798183, "environmentStepsPerSecond": 25256.03150209028, "learningRate": 0.000245703125, "loss": 189.84035682678223, "policyLoss": -0.0006198174669407308, "valueLoss": 379.7068614959717, "entropy": 1.2452604994177818, "approximateKl": 0.00011129081030958332, "clipFraction": 0.0, "explainedVariance": 0.1212839039359036, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 7859, "recentEpisodeCount": 100, "recentReturnMean": 2.474081468413733, "recentReturnMedian": -84.92185852943294, "recentLengthMean": 112.51, "recentLandingRate": 0.44 }, { "update": 141, "trainingStep": 577536, "elapsedSeconds": 22.853296165994834, "environmentStepsPerSecond": 25271.453002012022, "learningRate": 0.0002453125, "loss": 183.51643657684326, "policyLoss": -0.0005155531107448041, "valueLoss": 367.05886459350586, "entropy": 1.2482969462871552, "approximateKl": 0.00018800824545905925, "clipFraction": 0.0, "explainedVariance": 0.08695143029361141, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 7896, "recentEpisodeCount": 100, "recentReturnMean": -11.10713768763313, "recentReturnMedian": -87.41635929606855, "recentLengthMean": 110.23, "recentLandingRate": 0.38 }, { "update": 142, "trainingStep": 581632, "elapsedSeconds": 23.00043449999066, "environmentStepsPerSecond": 25287.87010524676, "learningRate": 0.00024492187499999997, "loss": 189.73562717437744, "policyLoss": -0.00043856207048520446, "valueLoss": 379.497127532959, "entropy": 1.2495096325874329, "approximateKl": 0.00023056668214849196, "clipFraction": 0.0, "explainedVariance": 0.08541589446267583, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 7933, "recentEpisodeCount": 100, "recentReturnMean": -3.6112483340879407, "recentReturnMedian": -86.40801073797047, "recentLengthMean": 109.64, "recentLandingRate": 0.41 }, { "update": 143, "trainingStep": 585728, "elapsedSeconds": 23.153679582988843, "environmentStepsPerSecond": 25297.40458317209, "learningRate": 0.00024453124999999996, "loss": 183.9756326675415, "policyLoss": -0.0002188411890529096, "valueLoss": 367.9766025543213, "entropy": 1.245003305375576, "approximateKl": 0.00016243364007095806, "clipFraction": 0.0, "explainedVariance": 0.20767618660354148, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 7972, "recentEpisodeCount": 100, "recentReturnMean": 26.514645713481297, "recentReturnMedian": 117.64915338298306, "recentLengthMean": 112.37, "recentLandingRate": 0.55 }, { "update": 144, "trainingStep": 589824, "elapsedSeconds": 23.303406416001962, "environmentStepsPerSecond": 25310.634396994432, "learningRate": 0.000244140625, "loss": 160.12306594848633, "policyLoss": -4.0411949157714844e-05, "valueLoss": 320.2710361480713, "entropy": 1.2411491498351097, "approximateKl": 1.9759132555918768e-05, "clipFraction": 0.0, "explainedVariance": 0.11349416234836052, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 8004, "recentEpisodeCount": 100, "recentReturnMean": 38.1133305283781, "recentReturnMedian": 119.09105997392908, "recentLengthMean": 109.7, "recentLandingRate": 0.6 }, { "update": 145, "trainingStep": 593920, "elapsedSeconds": 23.465865499980282, "environmentStepsPerSecond": 25309.95500679483, "learningRate": 0.00024375, "loss": 181.78741073608398, "policyLoss": -0.00020594403031282127, "valueLoss": 363.6000347137451, "entropy": 1.2402036413550377, "approximateKl": 2.0977302483515814e-05, "clipFraction": 0.0, "explainedVariance": 0.12128422936781802, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 8043, "recentEpisodeCount": 100, "recentReturnMean": 50.944118397353414, "recentReturnMedian": 120.73716651718132, "recentLengthMean": 111.95, "recentLandingRate": 0.66 }, { "update": 146, "trainingStep": 598016, "elapsedSeconds": 23.639957582985517, "environmentStepsPerSecond": 25296.83049983188, "learningRate": 0.00024335937499999998, "loss": 179.97072887420654, "policyLoss": -0.00013933968148194253, "valueLoss": 359.96672439575195, "entropy": 1.2494565322995186, "approximateKl": 3.9848589949542657e-05, "clipFraction": 0.0, "explainedVariance": 0.1410674709248334, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 8082, "recentEpisodeCount": 100, "recentReturnMean": 66.45542527912046, "recentReturnMedian": 120.28090982174035, "recentLengthMean": 115.7, "recentLandingRate": 0.73 }, { "update": 147, "trainingStep": 602112, "elapsedSeconds": 23.805043832981028, "environmentStepsPerSecond": 25293.463193115218, "learningRate": 0.00024296875, "loss": 191.25649166107178, "policyLoss": -7.87852331995964e-05, "valueLoss": 382.5380668640137, "entropy": 1.246213361620903, "approximateKl": 9.767190931597725e-06, "clipFraction": 0.0, "explainedVariance": 0.09862793073783305, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 8122, "recentEpisodeCount": 100, "recentReturnMean": 64.12252335520395, "recentReturnMedian": 120.43434908409836, "recentLengthMean": 110.6, "recentLandingRate": 0.72 }, { "update": 148, "trainingStep": 606208, "elapsedSeconds": 23.953971415990964, "environmentStepsPerSecond": 25307.20227858807, "learningRate": 0.00024257812499999998, "loss": 199.4067840576172, "policyLoss": -0.001246208616066724, "valueLoss": 398.8409824371338, "entropy": 1.245923973619938, "approximateKl": 0.0007304822902369779, "clipFraction": 0.000244140625, "explainedVariance": 0.06954358744991074, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 8162, "recentEpisodeCount": 100, "recentReturnMean": 55.17400484567363, "recentReturnMedian": 119.96871403884143, "recentLengthMean": 103.69, "recentLandingRate": 0.68 }, { "update": 149, "trainingStep": 610304, "elapsedSeconds": 24.109214165975573, "environmentStepsPerSecond": 25314.139058970206, "learningRate": 0.00024218749999999997, "loss": 156.95413970947266, "policyLoss": 0.0003693521721288562, "valueLoss": 313.9321460723877, "entropy": 1.2305293455719948, "approximateKl": 0.00022584753605769947, "clipFraction": 0.0, "explainedVariance": 0.15094369561230347, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 8196, "recentEpisodeCount": 100, "recentReturnMean": 48.768305182283804, "recentReturnMedian": 119.36719297520176, "recentLengthMean": 108.13, "recentLandingRate": 0.65 }, { "update": 150, "trainingStep": 614400, "elapsedSeconds": 24.2652378329949, "environmentStepsPerSecond": 25320.172183293562, "learningRate": 0.000241796875, "loss": 183.328839302063, "policyLoss": -0.00019024338689632714, "valueLoss": 366.6829032897949, "entropy": 1.2421769127249718, "approximateKl": 0.00014395219113794155, "clipFraction": 0.0, "explainedVariance": 0.0831711483429668, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 8231, "recentEpisodeCount": 100, "recentReturnMean": 35.87584664301889, "recentReturnMedian": 117.69347203942016, "recentLengthMean": 108.08, "recentLandingRate": 0.59 }, { "update": 151, "trainingStep": 618496, "elapsedSeconds": 24.41336341598071, "environmentStepsPerSecond": 25334.32159516126, "learningRate": 0.00024140624999999998, "loss": 155.18457984924316, "policyLoss": -0.000583214481594041, "valueLoss": 310.3950901031494, "entropy": 1.2382303699851036, "approximateKl": 0.0001804093917598948, "clipFraction": 0.0, "explainedVariance": 0.14183513865184683, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 8265, "recentEpisodeCount": 100, "recentReturnMean": 43.56751738959938, "recentReturnMedian": 117.79793757526204, "recentLengthMean": 114.74, "recentLandingRate": 0.63 }, { "update": 152, "trainingStep": 622592, "elapsedSeconds": 24.56358312498196, "environmentStepsPerSecond": 25346.139316572415, "learningRate": 0.00024101562499999996, "loss": 197.53666877746582, "policyLoss": -0.0005275416042422876, "valueLoss": 395.09933280944824, "entropy": 1.2471868842840195, "approximateKl": 0.0004647729510907084, "clipFraction": 0.0, "explainedVariance": 0.08790855392260111, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 8304, "recentEpisodeCount": 100, "recentReturnMean": 37.577440228442974, "recentReturnMedian": 119.4939540149062, "recentLengthMean": 112.47, "recentLandingRate": 0.6 }, { "update": 153, "trainingStep": 626688, "elapsedSeconds": 24.7103653329832, "environmentStepsPerSecond": 25361.34094154819, "learningRate": 0.00024062499999999998, "loss": 210.67226600646973, "policyLoss": -0.0002693016140256077, "valueLoss": 421.3700656890869, "entropy": 1.2499534860253334, "approximateKl": 0.00018733019169303589, "clipFraction": 0.0, "explainedVariance": 0.016213566835854287, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 8345, "recentEpisodeCount": 100, "recentReturnMean": 39.96198852985933, "recentReturnMedian": 119.64577590720728, "recentLengthMean": 108.62, "recentLandingRate": 0.61 }, { "update": 154, "trainingStep": 630784, "elapsedSeconds": 24.8676174999855, "environmentStepsPerSecond": 25365.67887938472, "learningRate": 0.00024023437499999997, "loss": 194.54246520996094, "policyLoss": -0.00011120983981527388, "valueLoss": 389.109899520874, "entropy": 1.23726786673069, "approximateKl": 6.347079761326313e-05, "clipFraction": 0.0, "explainedVariance": 0.0491976756343121, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 8385, "recentEpisodeCount": 100, "recentReturnMean": 44.86501057923033, "recentReturnMedian": 120.29354962179787, "recentLengthMean": 102.11, "recentLandingRate": 0.63 }, { "update": 155, "trainingStep": 634880, "elapsedSeconds": 25.02654949997668, "environmentStepsPerSecond": 25368.259415889177, "learningRate": 0.00023984374999999996, "loss": 202.5206127166748, "policyLoss": -0.00046616524923592806, "valueLoss": 405.06696128845215, "entropy": 1.2402414605021477, "approximateKl": 0.00022109196288511157, "clipFraction": 0.0, "explainedVariance": 0.03818196226417281, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 8423, "recentEpisodeCount": 100, "recentReturnMean": 34.65306205271904, "recentReturnMedian": 119.38340553059243, "recentLengthMean": 97.44, "recentLandingRate": 0.58 }, { "update": 156, "trainingStep": 638976, "elapsedSeconds": 25.177099374996033, "environmentStepsPerSecond": 25379.25399915536, "learningRate": 0.000239453125, "loss": 171.82801151275635, "policyLoss": -0.0006273006438277662, "valueLoss": 343.68220710754395, "entropy": 1.2462845295667648, "approximateKl": 0.0002796390726871323, "clipFraction": 6.103515625e-05, "explainedVariance": 0.10139033120138075, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 8460, "recentEpisodeCount": 100, "recentReturnMean": 43.62795957885595, "recentReturnMedian": 121.37536964571336, "recentLengthMean": 105.37, "recentLandingRate": 0.62 }, { "update": 157, "trainingStep": 643072, "elapsedSeconds": 25.328154415998142, "environmentStepsPerSecond": 25389.611474960584, "learningRate": 0.0002390625, "loss": 203.5317554473877, "policyLoss": -0.0002115594979841262, "valueLoss": 407.08864402770996, "entropy": 1.2354573979973793, "approximateKl": 0.00017977797324419953, "clipFraction": 6.103515625e-05, "explainedVariance": 0.05407544397906683, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 8502, "recentEpisodeCount": 100, "recentReturnMean": 45.08760133802862, "recentReturnMedian": 121.07366535096662, "recentLengthMean": 108.86, "recentLandingRate": 0.63 }, { "update": 158, "trainingStep": 647168, "elapsedSeconds": 25.483768040983705, "environmentStepsPerSecond": 25395.302569039493, "learningRate": 0.00023867187499999998, "loss": 201.94242477416992, "policyLoss": -0.00010586666758172214, "valueLoss": 403.90986251831055, "entropy": 1.2398519292473793, "approximateKl": 1.3502703950507566e-05, "clipFraction": 0.0, "explainedVariance": 0.05106738914412001, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 8546, "recentEpisodeCount": 100, "recentReturnMean": 58.0340548820468, "recentReturnMedian": 121.28628594108159, "recentLengthMean": 99.53, "recentLandingRate": 0.69 }, { "update": 159, "trainingStep": 651264, "elapsedSeconds": 25.638235291000456, "environmentStepsPerSecond": 25402.06034494921, "learningRate": 0.00023828125, "loss": 178.5975685119629, "policyLoss": -0.000855390855576843, "valueLoss": 357.22147941589355, "entropy": 1.2316123023629189, "approximateKl": 0.00025890316828736104, "clipFraction": 0.0, "explainedVariance": 0.09083726025676409, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 8585, "recentEpisodeCount": 100, "recentReturnMean": 58.31883726566335, "recentReturnMedian": 121.27592872921377, "recentLengthMean": 96.32, "recentLandingRate": 0.69 }, { "update": 160, "trainingStep": 655360, "elapsedSeconds": 25.788995040988084, "environmentStepsPerSecond": 25412.390012034004, "learningRate": 0.00023789062499999998, "loss": 203.85129261016846, "policyLoss": -0.00012086291098967195, "valueLoss": 407.72771072387695, "entropy": 1.2439634650945663, "approximateKl": 0.0001534458715468645, "clipFraction": 0.0, "explainedVariance": 0.07035245928752087, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 8628, "recentEpisodeCount": 100, "recentReturnMean": 47.999732529578395, "recentReturnMedian": 120.96665962855332, "recentLengthMean": 99.06, "recentLandingRate": 0.64 }, { "update": 161, "trainingStep": 659456, "elapsedSeconds": 25.939023332990473, "environmentStepsPerSecond": 25423.316504028615, "learningRate": 0.00023749999999999997, "loss": 180.92123126983643, "policyLoss": -0.0009474337566643953, "valueLoss": 361.8690986633301, "entropy": 1.2368683442473412, "approximateKl": 0.0007204983994597569, "clipFraction": 0.0, "explainedVariance": 0.06049917611031286, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 8665, "recentEpisodeCount": 100, "recentReturnMean": 41.7380713801847, "recentReturnMedian": 120.4527041555848, "recentLengthMean": 101.66, "recentLandingRate": 0.61 }, { "update": 162, "trainingStep": 663552, "elapsedSeconds": 26.089905082975747, "environmentStepsPerSecond": 25433.285322029886, "learningRate": 0.000237109375, "loss": 187.33248615264893, "policyLoss": 0.00020401272922754288, "valueLoss": 374.6892890930176, "entropy": 1.2360934242606163, "approximateKl": 0.0005840691956109367, "clipFraction": 0.0, "explainedVariance": 0.042164558555518705, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 8705, "recentEpisodeCount": 100, "recentReturnMean": 49.70310123369141, "recentReturnMedian": 120.92587979417294, "recentLengthMean": 106.26, "recentLandingRate": 0.65 }, { "update": 163, "trainingStep": 667648, "elapsedSeconds": 26.251462540996727, "environmentStepsPerSecond": 25432.792514220448, "learningRate": 0.00023671874999999998, "loss": 180.3148717880249, "policyLoss": -0.0003657438501249999, "valueLoss": 360.6549892425537, "entropy": 1.2257226705551147, "approximateKl": 5.7282621128251776e-05, "clipFraction": 0.0, "explainedVariance": 0.04431650222517847, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 8744, "recentEpisodeCount": 100, "recentReturnMean": 49.60608113215712, "recentReturnMedian": 121.07557899845415, "recentLengthMean": 103.09, "recentLandingRate": 0.65 }, { "update": 164, "trainingStep": 671744, "elapsedSeconds": 26.40434133299277, "environmentStepsPerSecond": 25440.664909169387, "learningRate": 0.00023632812499999997, "loss": 195.00743961334229, "policyLoss": -0.00011130893835797906, "valueLoss": 390.03965950012207, "entropy": 1.2278369441628456, "approximateKl": 8.531919957022183e-05, "clipFraction": 0.0, "explainedVariance": 0.03782609348472854, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 8787, "recentEpisodeCount": 100, "recentReturnMean": 51.54178884327251, "recentReturnMedian": 121.18449565130868, "recentLengthMean": 99.53, "recentLandingRate": 0.66 }, { "update": 165, "trainingStep": 675840, "elapsedSeconds": 26.554231999994954, "environmentStepsPerSecond": 25451.31035987516, "learningRate": 0.00023593749999999998, "loss": 172.84598922729492, "policyLoss": -0.0003695502527989447, "valueLoss": 345.71740531921387, "entropy": 1.234258234500885, "approximateKl": 0.00012816059825127013, "clipFraction": 0.0, "explainedVariance": 0.07385028533064786, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 8827, "recentEpisodeCount": 100, "recentReturnMean": 59.66303618645601, "recentReturnMedian": 121.03183567139786, "recentLengthMean": 105.03, "recentLandingRate": 0.7 }, { "update": 166, "trainingStep": 679936, "elapsedSeconds": 26.702525082975626, "environmentStepsPerSecond": 25463.359659326667, "learningRate": 0.00023554687499999997, "loss": 199.62854957580566, "policyLoss": -0.0008811901207081974, "valueLoss": 399.28359603881836, "entropy": 1.2365869656205177, "approximateKl": 0.0007610953616676852, "clipFraction": 6.103515625e-05, "explainedVariance": 0.0403127258818915, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 8867, "recentEpisodeCount": 100, "recentReturnMean": 55.99083695255424, "recentReturnMedian": 121.07288833206985, "recentLengthMean": 106.66, "recentLandingRate": 0.68 }, { "update": 167, "trainingStep": 684032, "elapsedSeconds": 26.85373662499478, "environmentStepsPerSecond": 25472.507217610837, "learningRate": 0.00023515624999999996, "loss": 186.353835105896, "policyLoss": -0.0005452619516290724, "valueLoss": 372.73339462280273, "entropy": 1.2316457778215408, "approximateKl": 0.0006062095271772705, "clipFraction": 0.0, "explainedVariance": 0.06160731305379796, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 8904, "recentEpisodeCount": 100, "recentReturnMean": 51.9859257297877, "recentReturnMedian": 121.07288833206985, "recentLengthMean": 102.82, "recentLandingRate": 0.66 }, { "update": 168, "trainingStep": 688128, "elapsedSeconds": 27.014536415983457, "environmentStepsPerSecond": 25472.5081861061, "learningRate": 0.000234765625, "loss": 171.9941005706787, "policyLoss": -0.000779255191446282, "valueLoss": 344.0140018463135, "entropy": 1.212186798453331, "approximateKl": 0.00018633675790624693, "clipFraction": 0.0, "explainedVariance": 0.05688951042340962, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 8943, "recentEpisodeCount": 100, "recentReturnMean": 58.97242303518535, "recentReturnMedian": 121.96864476185874, "recentLengthMean": 97.78, "recentLandingRate": 0.69 }, { "update": 169, "trainingStep": 692224, "elapsedSeconds": 27.172337083000457, "environmentStepsPerSecond": 25475.32065002494, "learningRate": 0.000234375, "loss": 153.42120456695557, "policyLoss": -0.0005829688743688166, "valueLoss": 306.8676414489746, "entropy": 1.2030215933918953, "approximateKl": 0.0004315583319112193, "clipFraction": 0.0, "explainedVariance": 0.07152865351570648, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 8982, "recentEpisodeCount": 100, "recentReturnMean": 62.670773765440245, "recentReturnMedian": 121.51259476563428, "recentLengthMean": 102.77, "recentLandingRate": 0.7 }, { "update": 170, "trainingStep": 696320, "elapsedSeconds": 27.324524208001094, "environmentStepsPerSecond": 25483.334849655148, "learningRate": 0.00023398437499999998, "loss": 166.63715744018555, "policyLoss": -0.0004411929694470018, "valueLoss": 333.29967308044434, "entropy": 1.223748005926609, "approximateKl": 0.00028908396780025214, "clipFraction": 0.0, "explainedVariance": 0.060504431180198104, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 9020, "recentEpisodeCount": 100, "recentReturnMean": 62.33650994918353, "recentReturnMedian": 121.34317928506061, "recentLengthMean": 107.87, "recentLandingRate": 0.7 }, { "update": 171, "trainingStep": 700416, "elapsedSeconds": 27.47825487499358, "environmentStepsPerSecond": 25489.82834559153, "learningRate": 0.00023359375, "loss": 167.36150646209717, "policyLoss": -0.0009845565655268729, "valueLoss": 334.7492847442627, "entropy": 1.2152929082512856, "approximateKl": 0.0005103922921989579, "clipFraction": 0.0, "explainedVariance": 0.044411554009357146, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 9059, "recentEpisodeCount": 100, "recentReturnMean": 75.22314334125505, "recentReturnMedian": 122.45709585293662, "recentLengthMean": 108.64, "recentLandingRate": 0.76 }, { "update": 172, "trainingStep": 704512, "elapsedSeconds": 27.63302224999643, "environmentStepsPerSecond": 25495.293045627357, "learningRate": 0.00023320312499999998, "loss": 210.694167137146, "policyLoss": -0.0003805230953730643, "valueLoss": 421.4137325286865, "entropy": 1.2320299223065376, "approximateKl": 0.00021446904065669514, "clipFraction": 0.0, "explainedVariance": 0.03645028571492892, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 9107, "recentEpisodeCount": 100, "recentReturnMean": 67.16535532320552, "recentReturnMedian": 122.42330918647349, "recentLengthMean": 100.79, "recentLandingRate": 0.73 }, { "update": 173, "trainingStep": 708608, "elapsedSeconds": 27.787815957999555, "environmentStepsPerSecond": 25500.672707457095, "learningRate": 0.00023281249999999997, "loss": 163.53276824951172, "policyLoss": -0.00011169479694217443, "valueLoss": 327.0901584625244, "entropy": 1.2198064401745796, "approximateKl": 0.00026166746829403564, "clipFraction": 0.0, "explainedVariance": 0.05102662091494392, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 9146, "recentEpisodeCount": 100, "recentReturnMean": 63.415735475956936, "recentReturnMedian": 122.5252974977484, "recentLengthMean": 92.17, "recentLandingRate": 0.71 }, { "update": 174, "trainingStep": 712704, "elapsedSeconds": 27.94599433298572, "environmentStepsPerSecond": 25502.903618597258, "learningRate": 0.000232421875, "loss": 183.0484218597412, "policyLoss": -0.0009439072455279529, "valueLoss": 366.1229610443115, "entropy": 1.2117430716753006, "approximateKl": 0.0005502573985722847, "clipFraction": 0.00616455078125, "explainedVariance": 0.04136829218455007, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 9186, "recentEpisodeCount": 100, "recentReturnMean": 59.47858444028177, "recentReturnMedian": 123.00976989534684, "recentLengthMean": 89.03, "recentLandingRate": 0.69 }, { "update": 175, "trainingStep": 716800, "elapsedSeconds": 28.115911332977703, "environmentStepsPerSecond": 25494.460823656504, "learningRate": 0.00023203124999999998, "loss": 141.75859689712524, "policyLoss": -0.0012689075083471835, "valueLoss": 283.5434503555298, "entropy": 1.186057984828949, "approximateKl": 0.0014740649166924413, "clipFraction": 0.00579833984375, "explainedVariance": 0.02391899859870872, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 9222, "recentEpisodeCount": 100, "recentReturnMean": 63.89992828786857, "recentReturnMedian": 122.26047036878299, "recentLengthMean": 100.76, "recentLandingRate": 0.7 }, { "update": 176, "trainingStep": 720896, "elapsedSeconds": 28.280076832976192, "environmentStepsPerSecond": 25491.302737883438, "learningRate": 0.00023164062499999997, "loss": 203.27688598632812, "policyLoss": 0.00010022951755672693, "valueLoss": 406.5775833129883, "entropy": 1.2005400508642197, "approximateKl": 0.00016129895084304735, "clipFraction": 0.0, "explainedVariance": 0.05101434755851497, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 9274, "recentEpisodeCount": 100, "recentReturnMean": 65.96018740980006, "recentReturnMedian": 122.12381230993196, "recentLengthMean": 103.89, "recentLandingRate": 0.71 }, { "update": 177, "trainingStep": 724992, "elapsedSeconds": 28.439762041001813, "environmentStepsPerSecond": 25492.196416931118, "learningRate": 0.00023124999999999998, "loss": 273.1215982437134, "policyLoss": -0.00048383508692495525, "valueLoss": 546.268238067627, "entropy": 1.2039977088570595, "approximateKl": 0.00016309761485899799, "clipFraction": 0.0, "explainedVariance": 0.04215178798470831, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 9325, "recentEpisodeCount": 100, "recentReturnMean": 55.16352189457189, "recentReturnMedian": 122.26696718297899, "recentLengthMean": 89.67, "recentLandingRate": 0.67 }, { "update": 178, "trainingStep": 729088, "elapsedSeconds": 28.611916790978285, "environmentStepsPerSecond": 25481.96981440583, "learningRate": 0.00023085937499999997, "loss": 229.40400981903076, "policyLoss": -0.0007511546718887985, "valueLoss": 458.8333339691162, "entropy": 1.190726175904274, "approximateKl": 0.0005756954997195862, "clipFraction": 0.00274658203125, "explainedVariance": 0.02843477979408926, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 9373, "recentEpisodeCount": 100, "recentReturnMean": 44.71608535114465, "recentReturnMedian": 122.5464518192457, "recentLengthMean": 84.0, "recentLandingRate": 0.62 }, { "update": 179, "trainingStep": 733184, "elapsedSeconds": 28.77722512499895, "environmentStepsPerSecond": 25477.925575356418, "learningRate": 0.00023046874999999996, "loss": 229.22445106506348, "policyLoss": -0.0005315957241691649, "valueLoss": 458.47399139404297, "entropy": 1.201554723083973, "approximateKl": 0.00041991937905550003, "clipFraction": 0.00152587890625, "explainedVariance": 0.03760789938044906, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 9421, "recentEpisodeCount": 100, "recentReturnMean": 53.28073931056147, "recentReturnMedian": 123.69615482189693, "recentLengthMean": 85.72, "recentLandingRate": 0.66 }, { "update": 180, "trainingStep": 737280, "elapsedSeconds": 28.93880612499197, "environmentStepsPerSecond": 25477.20859027679, "learningRate": 0.000230078125, "loss": 207.1749029159546, "policyLoss": -0.00045345519902184606, "valueLoss": 414.3746757507324, "entropy": 1.1978939846158028, "approximateKl": 0.00025642619948484935, "clipFraction": 0.0, "explainedVariance": 0.035604671458408954, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 9466, "recentEpisodeCount": 100, "recentReturnMean": 55.1326835529368, "recentReturnMedian": 122.4169803733239, "recentLengthMean": 87.21, "recentLandingRate": 0.67 }, { "update": 181, "trainingStep": 741376, "elapsedSeconds": 29.103033499995945, "environmentStepsPerSecond": 25474.182957597986, "learningRate": 0.0002296875, "loss": 162.9433069229126, "policyLoss": -2.78348452411592e-05, "valueLoss": 325.91034507751465, "entropy": 1.1837287619709969, "approximateKl": 0.0001726756636344362, "clipFraction": 0.0, "explainedVariance": 0.06975279863625328, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 9507, "recentEpisodeCount": 100, "recentReturnMean": 63.66154110385738, "recentReturnMedian": 122.98433011234738, "recentLengthMean": 89.19, "recentLandingRate": 0.71 }, { "update": 182, "trainingStep": 745472, "elapsedSeconds": 29.270726207992993, "environmentStepsPerSecond": 25468.17577065898, "learningRate": 0.00022929687499999998, "loss": 187.9701910018921, "policyLoss": -0.00022307713516056538, "valueLoss": 375.9646167755127, "entropy": 1.1894400417804718, "approximateKl": 9.596022573532537e-05, "clipFraction": 0.0, "explainedVariance": 0.06662693463774749, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 9551, "recentEpisodeCount": 100, "recentReturnMean": 64.71270327544015, "recentReturnMedian": 122.94427786511369, "recentLengthMean": 93.23, "recentLandingRate": 0.71 }, { "update": 183, "trainingStep": 749568, "elapsedSeconds": 29.430640457983827, "environmentStepsPerSecond": 25468.966639380767, "learningRate": 0.00022890625, "loss": 187.616605758667, "policyLoss": -0.0002218532026745379, "valueLoss": 375.2577724456787, "entropy": 1.205437421798706, "approximateKl": 0.00011421258022892289, "clipFraction": 0.0, "explainedVariance": 0.06544844560984686, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 9592, "recentEpisodeCount": 100, "recentReturnMean": 60.38773310692195, "recentReturnMedian": 122.24080200633034, "recentLengthMean": 96.8, "recentLandingRate": 0.69 }, { "update": 184, "trainingStep": 753664, "elapsedSeconds": 29.5955479159893, "environmentStepsPerSecond": 25465.451835504802, "learningRate": 0.00022851562499999999, "loss": 193.79797554016113, "policyLoss": -0.0007953508174978197, "valueLoss": 387.6214084625244, "entropy": 1.1932413578033447, "approximateKl": 0.0007067095648380928, "clipFraction": 0.0, "explainedVariance": 0.07719678179344014, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 9639, "recentEpisodeCount": 100, "recentReturnMean": 63.40458865845467, "recentReturnMedian": 122.5130532408566, "recentLengthMean": 98.07, "recentLandingRate": 0.7 }, { "update": 185, "trainingStep": 757760, "elapsedSeconds": 29.759841457998846, "environmentStepsPerSecond": 25462.50123910957, "learningRate": 0.00022812499999999997, "loss": 180.97601699829102, "policyLoss": -0.0012630854034796357, "valueLoss": 361.97859382629395, "entropy": 1.2017308920621872, "approximateKl": 0.001136974820838077, "clipFraction": 0.0010986328125, "explainedVariance": 0.08985829709043192, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 9685, "recentEpisodeCount": 100, "recentReturnMean": 73.36873166762842, "recentReturnMedian": 123.70567217833013, "recentLengthMean": 94.2, "recentLandingRate": 0.75 }, { "update": 186, "trainingStep": 761856, "elapsedSeconds": 29.978610374993877, "environmentStepsPerSecond": 25413.31937905596, "learningRate": 0.000227734375, "loss": 153.40306663513184, "policyLoss": -0.000192247360246256, "valueLoss": 306.8306198120117, "entropy": 1.2048190161585808, "approximateKl": 0.0004993134461983573, "clipFraction": 0.0, "explainedVariance": 0.01775729923701752, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 9730, "recentEpisodeCount": 100, "recentReturnMean": 84.4417484635182, "recentReturnMedian": 124.1140364720195, "recentLengthMean": 89.82, "recentLandingRate": 0.8 }, { "update": 187, "trainingStep": 765952, "elapsedSeconds": 30.16497483299463, "environmentStepsPerSecond": 25392.09809524512, "learningRate": 0.00022734374999999998, "loss": 217.9987668991089, "policyLoss": -0.00035370764089748263, "valueLoss": 436.0221538543701, "entropy": 1.1953982710838318, "approximateKl": 0.0001359926573059056, "clipFraction": 0.0, "explainedVariance": -2.4070391340558217e-05, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 9778, "recentEpisodeCount": 100, "recentReturnMean": 71.53476169758375, "recentReturnMedian": 123.39132552430965, "recentLengthMean": 85.55, "recentLandingRate": 0.74 }, { "update": 188, "trainingStep": 770048, "elapsedSeconds": 30.480335125001147, "environmentStepsPerSecond": 25263.76422181713, "learningRate": 0.00022695312499999997, "loss": 192.8561725616455, "policyLoss": -0.0011204409529455006, "valueLoss": 385.7384605407715, "entropy": 1.193799965083599, "approximateKl": 0.001868535800895188, "clipFraction": 0.0086669921875, "explainedVariance": -0.0050871092389397354, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 9821, "recentEpisodeCount": 100, "recentReturnMean": 58.16465440028989, "recentReturnMedian": 122.83257929049432, "recentLengthMean": 88.49, "recentLandingRate": 0.68 }, { "update": 189, "trainingStep": 774144, "elapsedSeconds": 30.853566582984058, "environmentStepsPerSecond": 25090.90798037415, "learningRate": 0.00022656249999999998, "loss": 190.19433975219727, "policyLoss": -0.0009048015635926276, "valueLoss": 380.4144096374512, "entropy": 1.1958874240517616, "approximateKl": 0.0005750657073804177, "clipFraction": 0.0, "explainedVariance": 0.036493752652877465, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 9868, "recentEpisodeCount": 100, "recentReturnMean": 60.67410659659838, "recentReturnMedian": 122.92834623949602, "recentLengthMean": 89.08, "recentLandingRate": 0.69 }, { "update": 190, "trainingStep": 778240, "elapsedSeconds": 31.05678283298039, "environmentStepsPerSecond": 25058.61615432868, "learningRate": 0.00022617187499999997, "loss": 197.56403923034668, "policyLoss": -0.000534282939042896, "valueLoss": 395.1529483795166, "entropy": 1.1901284083724022, "approximateKl": 0.0004781096249644179, "clipFraction": 0.0, "explainedVariance": 0.01276768850171317, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 9911, "recentEpisodeCount": 100, "recentReturnMean": 52.438271353474775, "recentReturnMedian": 122.61289662134368, "recentLengthMean": 92.94, "recentLandingRate": 0.65 }, { "update": 191, "trainingStep": 782336, "elapsedSeconds": 31.447212874976685, "environmentStepsPerSecond": 24877.753176737766, "learningRate": 0.00022578124999999996, "loss": 156.71536350250244, "policyLoss": -0.000651194277452305, "valueLoss": 313.4556713104248, "entropy": 1.1821329891681671, "approximateKl": 0.0006296901483437978, "clipFraction": 0.0, "explainedVariance": 0.01810147597620748, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 9955, "recentEpisodeCount": 100, "recentReturnMean": 68.03521874762583, "recentReturnMedian": 123.30972657492384, "recentLengthMean": 89.94, "recentLandingRate": 0.73 }, { "update": 192, "trainingStep": 786432, "elapsedSeconds": 31.672898415999953, "environmentStepsPerSecond": 24829.808427091226, "learningRate": 0.00022539062499999998, "loss": 134.39734601974487, "policyLoss": -0.0005244363564997911, "valueLoss": 268.819637298584, "entropy": 1.194741740822792, "approximateKl": 0.00023550249534309842, "clipFraction": 0.0, "explainedVariance": 0.06451205285693362, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 9996, "recentEpisodeCount": 100, "recentReturnMean": 83.23639569889896, "recentReturnMedian": 123.53813578665722, "recentLengthMean": 98.82, "recentLandingRate": 0.8 }, { "update": 193, "trainingStep": 790528, "elapsedSeconds": 31.83641258298303, "environmentStepsPerSecond": 24830.93840863676, "learningRate": 0.000225, "loss": 147.65547943115234, "policyLoss": -0.0004556443600449711, "valueLoss": 295.335693359375, "entropy": 1.1910743117332458, "approximateKl": 0.0004240562775521539, "clipFraction": 0.0, "explainedVariance": 0.00551506088856113, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 10039, "recentEpisodeCount": 100, "recentReturnMean": 83.54140366017, "recentReturnMedian": 123.73413579515181, "recentLengthMean": 97.4, "recentLandingRate": 0.8 }, { "update": 194, "trainingStep": 794624, "elapsedSeconds": 31.997714582976187, "environmentStepsPerSecond": 24833.773610280452, "learningRate": 0.000224609375, "loss": 128.35747718811035, "policyLoss": -0.00019598263315856457, "valueLoss": 256.7392883300781, "entropy": 1.1971832662820816, "approximateKl": 6.296778155956417e-05, "clipFraction": 0.0, "explainedVariance": 0.013751632274725978, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 10080, "recentEpisodeCount": 100, "recentReturnMean": 93.4221666015645, "recentReturnMedian": 124.2593207352329, "recentLengthMean": 91.1, "recentLandingRate": 0.85 }, { "update": 195, "trainingStep": 798720, "elapsedSeconds": 32.153438207984436, "environmentStepsPerSecond": 24840.889326779976, "learningRate": 0.00022421874999999997, "loss": 170.98431015014648, "policyLoss": -0.0007627283048350364, "valueLoss": 341.9942111968994, "entropy": 1.2032995000481606, "approximateKl": 0.0005269329958537128, "clipFraction": 0.0, "explainedVariance": -0.0031496954547971523, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 10128, "recentEpisodeCount": 100, "recentReturnMean": 89.42052917525307, "recentReturnMedian": 124.13637695438229, "recentLengthMean": 100.69, "recentLandingRate": 0.82 }, { "update": 196, "trainingStep": 802816, "elapsedSeconds": 32.30134191599791, "environmentStepsPerSecond": 24853.951953073156, "learningRate": 0.000223828125, "loss": 173.61532306671143, "policyLoss": -0.0018419960688333958, "valueLoss": 347.2582092285156, "entropy": 1.1938327625393867, "approximateKl": 0.0019258473730587866, "clipFraction": 0.0084228515625, "explainedVariance": 0.01407399428852818, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 10174, "recentEpisodeCount": 100, "recentReturnMean": 81.435651026843, "recentReturnMedian": 124.13637695438229, "recentLengthMean": 94.74, "recentLandingRate": 0.78 }, { "update": 197, "trainingStep": 806912, "elapsedSeconds": 32.45809120798367, "environmentStepsPerSecond": 24860.118693656423, "learningRate": 0.0002234375, "loss": 155.97754955291748, "policyLoss": 0.00016183030675165355, "valueLoss": 311.97868156433105, "entropy": 1.1953674629330635, "approximateKl": 0.00018996914150193334, "clipFraction": 0.0, "explainedVariance": 0.030478040012767105, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 10224, "recentEpisodeCount": 100, "recentReturnMean": 88.64536894818251, "recentReturnMedian": 124.71478393836878, "recentLengthMean": 86.35, "recentLandingRate": 0.82 }, { "update": 198, "trainingStep": 811008, "elapsedSeconds": 32.61072095797863, "environmentStepsPerSecond": 24869.367379060554, "learningRate": 0.00022304687499999997, "loss": 127.86348962783813, "policyLoss": -0.00023940627579577267, "valueLoss": 255.75148391723633, "entropy": 1.2013623341917992, "approximateKl": 7.621094846399501e-05, "clipFraction": 0.0, "explainedVariance": 0.034613597390072304, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 10270, "recentEpisodeCount": 100, "recentReturnMean": 98.6082515095896, "recentReturnMedian": 125.1073376336135, "recentLengthMean": 86.13, "recentLandingRate": 0.87 }, { "update": 199, "trainingStep": 815104, "elapsedSeconds": 32.7689477079839, "environmentStepsPerSecond": 24874.280592214633, "learningRate": 0.00022265624999999998, "loss": 154.96481704711914, "policyLoss": -0.00048367923591285944, "valueLoss": 309.95460510253906, "entropy": 1.2002520114183426, "approximateKl": 0.00014609909703722224, "clipFraction": 0.0, "explainedVariance": 0.033629323612766715, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 10317, "recentEpisodeCount": 100, "recentReturnMean": 96.23834705092514, "recentReturnMedian": 124.86369200935587, "recentLengthMean": 88.81, "recentLandingRate": 0.86 }, { "update": 200, "trainingStep": 819200, "elapsedSeconds": 32.92788420798024, "environmentStepsPerSecond": 24878.610323874458, "learningRate": 0.000222265625, "loss": 173.16246223449707, "policyLoss": -0.00027518143178895116, "valueLoss": 346.34917068481445, "entropy": 1.1848558336496353, "approximateKl": 0.00015523781985393725, "clipFraction": 0.0, "explainedVariance": 0.020111509758259483, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 10363, "recentEpisodeCount": 100, "recentReturnMean": 88.24920580308267, "recentReturnMedian": 125.27814557030797, "recentLengthMean": 84.6, "recentLandingRate": 0.82 }, { "update": 201, "trainingStep": 823296, "elapsedSeconds": 33.08641345798969, "environmentStepsPerSecond": 24883.204734334566, "learningRate": 0.00022187499999999996, "loss": 178.45134830474854, "policyLoss": -0.0011354346643202007, "valueLoss": 356.9286193847656, "entropy": 1.1828580796718597, "approximateKl": 0.001410557084454922, "clipFraction": 0.004150390625, "explainedVariance": 0.02182109474483951, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 10407, "recentEpisodeCount": 100, "recentReturnMean": 79.72224793425522, "recentReturnMedian": 124.91095918649808, "recentLengthMean": 88.08, "recentLandingRate": 0.78 }, { "update": 202, "trainingStep": 827392, "elapsedSeconds": 33.25731687498046, "environmentStepsPerSecond": 24878.495252948338, "learningRate": 0.00022148437499999997, "loss": 145.93235301971436, "policyLoss": -0.0005869937594980001, "valueLoss": 291.8893585205078, "entropy": 1.1739422380924225, "approximateKl": 0.0006823570838605519, "clipFraction": 0.0, "explainedVariance": 0.014329076707443655, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 10453, "recentEpisodeCount": 100, "recentReturnMean": 81.68478095790618, "recentReturnMedian": 124.79504337767139, "recentLengthMean": 87.61, "recentLandingRate": 0.79 }, { "update": 203, "trainingStep": 831488, "elapsedSeconds": 33.418546290980885, "environmentStepsPerSecond": 24881.034404072954, "learningRate": 0.00022109375, "loss": 121.94407844543457, "policyLoss": -5.386245902627707e-07, "valueLoss": 243.91157817840576, "entropy": 1.1710920333862305, "approximateKl": 6.844595918664709e-05, "clipFraction": 0.0, "explainedVariance": 0.021081839486069898, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 10500, "recentEpisodeCount": 100, "recentReturnMean": 100.79222387808069, "recentReturnMedian": 125.35727481950016, "recentLengthMean": 87.12, "recentLandingRate": 0.88 }, { "update": 204, "trainingStep": 835584, "elapsedSeconds": 33.58660979097476, "environmentStepsPerSecond": 24878.485956166205, "learningRate": 0.00022070312499999995, "loss": 136.15424919128418, "policyLoss": -0.0001629436737857759, "valueLoss": 272.3322162628174, "entropy": 1.1694444194436073, "approximateKl": 0.00012475501353037544, "clipFraction": 0.0, "explainedVariance": 0.004769661802222047, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 10543, "recentEpisodeCount": 100, "recentReturnMean": 104.20834822763237, "recentReturnMedian": 125.98349278396927, "recentLengthMean": 89.22, "recentLandingRate": 0.89 }, { "update": 205, "trainingStep": 839680, "elapsedSeconds": 33.74939920799807, "environmentStepsPerSecond": 24879.85029970576, "learningRate": 0.00022031249999999997, "loss": 148.17448472976685, "policyLoss": -0.0002813598548527807, "valueLoss": 296.37317180633545, "entropy": 1.1818284466862679, "approximateKl": 0.0001650111807975918, "clipFraction": 0.0, "explainedVariance": 0.026899650407254505, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 10597, "recentEpisodeCount": 100, "recentReturnMean": 99.6607500844475, "recentReturnMedian": 125.81295075081289, "recentLengthMean": 88.98, "recentLandingRate": 0.87 }, { "update": 206, "trainingStep": 843776, "elapsedSeconds": 33.9040323329973, "environmentStepsPerSecond": 24887.187214565918, "learningRate": 0.000219921875, "loss": 148.79553604125977, "policyLoss": -0.0002627754001878202, "valueLoss": 297.6153793334961, "entropy": 1.1891175657510757, "approximateKl": 7.130645099096e-05, "clipFraction": 0.0, "explainedVariance": 0.027345682399166016, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 10651, "recentEpisodeCount": 100, "recentReturnMean": 105.11262547032486, "recentReturnMedian": 126.00219477862993, "recentLengthMean": 81.55, "recentLandingRate": 0.9 }, { "update": 207, "trainingStep": 847872, "elapsedSeconds": 34.063603082991904, "environmentStepsPerSecond": 24890.848978431935, "learningRate": 0.00021953124999999995, "loss": 118.06621789932251, "policyLoss": -0.0004261878493707627, "valueLoss": 236.15701961517334, "entropy": 1.1865083500742912, "approximateKl": 0.00010284642849001102, "clipFraction": 0.0, "explainedVariance": 0.018258576358167633, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 10699, "recentEpisodeCount": 100, "recentReturnMean": 109.20680413360795, "recentReturnMedian": 125.64817673899233, "recentLengthMean": 74.49, "recentLandingRate": 0.92 }, { "update": 208, "trainingStep": 851968, "elapsedSeconds": 34.229755040985765, "environmentStepsPerSecond": 24889.690241133103, "learningRate": 0.000219140625, "loss": 142.49049854278564, "policyLoss": -0.0007117442146409303, "valueLoss": 285.00586223602295, "entropy": 1.172187477350235, "approximateKl": 0.00017981826022150926, "clipFraction": 0.0, "explainedVariance": 0.0025120764962197617, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 10746, "recentEpisodeCount": 100, "recentReturnMean": 105.08124562205877, "recentReturnMedian": 125.57072337716818, "recentLengthMean": 75.87, "recentLandingRate": 0.9 }, { "update": 209, "trainingStep": 856064, "elapsedSeconds": 34.39331804099493, "environmentStepsPerSecond": 24890.416184318685, "learningRate": 0.00021875, "loss": 170.41478729248047, "policyLoss": -7.721211295574903e-05, "valueLoss": 340.85319328308105, "entropy": 1.173354871571064, "approximateKl": 0.000764235584938433, "clipFraction": 0.0, "explainedVariance": 0.004091644687147178, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 10803, "recentEpisodeCount": 100, "recentReturnMean": 98.11526665118188, "recentReturnMedian": 126.71893451409414, "recentLengthMean": 83.51, "recentLandingRate": 0.86 }, { "update": 210, "trainingStep": 860160, "elapsedSeconds": 34.55669833297725, "environmentStepsPerSecond": 24891.266859807452, "learningRate": 0.00021835937499999997, "loss": 98.84568738937378, "policyLoss": -0.0006800218834541738, "valueLoss": 197.71620559692383, "entropy": 1.1735805720090866, "approximateKl": 0.00019548282216419466, "clipFraction": 0.0, "explainedVariance": 0.017740001970921515, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 10846, "recentEpisodeCount": 100, "recentReturnMean": 105.8054252432139, "recentReturnMedian": 125.96243783237878, "recentLengthMean": 86.66, "recentLandingRate": 0.9 }, { "update": 211, "trainingStep": 864256, "elapsedSeconds": 34.720647540991195, "environmentStepsPerSecond": 24891.701659067832, "learningRate": 0.00021796874999999998, "loss": 158.90463161468506, "policyLoss": -0.000564838876016438, "valueLoss": 317.8340129852295, "entropy": 1.1811764314770699, "approximateKl": 0.0003579592957976274, "clipFraction": 0.0, "explainedVariance": 0.013846778094564915, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 10898, "recentEpisodeCount": 100, "recentReturnMean": 100.7257384918951, "recentReturnMedian": 125.44005579443183, "recentLengthMean": 82.84, "recentLandingRate": 0.88 }, { "update": 212, "trainingStep": 868352, "elapsedSeconds": 34.88863391597988, "environmentStepsPerSecond": 24889.251957849596, "learningRate": 0.000217578125, "loss": 177.89291381835938, "policyLoss": -0.00046324252616614103, "valueLoss": 355.81030082702637, "entropy": 1.1774022802710533, "approximateKl": 0.0004934325916110538, "clipFraction": 0.0001220703125, "explainedVariance": 0.012680761783457895, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 10951, "recentEpisodeCount": 100, "recentReturnMean": 89.90293354234906, "recentReturnMedian": 125.08404372271616, "recentLengthMean": 79.8, "recentLandingRate": 0.83 }, { "update": 213, "trainingStep": 872448, "elapsedSeconds": 35.04959133299417, "environmentStepsPerSecond": 24891.81661809321, "learningRate": 0.00021718749999999996, "loss": 188.79464530944824, "policyLoss": -0.00035263661993667483, "valueLoss": 377.6134967803955, "entropy": 1.1752367541193962, "approximateKl": 0.0003402045294933487, "clipFraction": 0.0, "explainedVariance": 0.012481834176626738, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 11007, "recentEpisodeCount": 100, "recentReturnMean": 86.17711333273851, "recentReturnMedian": 125.59237295738421, "recentLengthMean": 80.43, "recentLandingRate": 0.81 }, { "update": 214, "trainingStep": 876544, "elapsedSeconds": 35.20544195797993, "environmentStepsPerSecond": 24897.968928957474, "learningRate": 0.00021679687499999998, "loss": 200.04515171051025, "policyLoss": -0.0002514552907086909, "valueLoss": 400.1144733428955, "entropy": 1.183342307806015, "approximateKl": 0.00013874109572498128, "clipFraction": 0.0, "explainedVariance": 0.009331459542603948, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 11062, "recentEpisodeCount": 100, "recentReturnMean": 80.21424477592903, "recentReturnMedian": 125.44312156084925, "recentLengthMean": 76.61, "recentLandingRate": 0.78 }, { "update": 215, "trainingStep": 880640, "elapsedSeconds": 35.37246020798921, "environmentStepsPerSecond": 24896.204415012646, "learningRate": 0.00021640625, "loss": 171.8342456817627, "policyLoss": -0.00018771256145555526, "valueLoss": 343.69227600097656, "entropy": 1.1705114170908928, "approximateKl": 0.00012460770085453987, "clipFraction": 0.0, "explainedVariance": 0.004861817127261303, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 11114, "recentEpisodeCount": 100, "recentReturnMean": 84.73734556799907, "recentReturnMedian": 126.03899528761394, "recentLengthMean": 72.4, "recentLandingRate": 0.8 }, { "update": 216, "trainingStep": 884736, "elapsedSeconds": 35.53920849997667, "environmentStepsPerSecond": 24894.64558560951, "learningRate": 0.00021601562499999995, "loss": 171.6028938293457, "policyLoss": -0.0008376868790946901, "valueLoss": 343.2308940887451, "entropy": 1.171533241868019, "approximateKl": 0.00047988331061787903, "clipFraction": 0.00030517578125, "explainedVariance": 0.007056050477435072, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 11167, "recentEpisodeCount": 100, "recentReturnMean": 86.81113050804008, "recentReturnMedian": 125.21647769259289, "recentLengthMean": 75.23, "recentLandingRate": 0.81 }, { "update": 217, "trainingStep": 888832, "elapsedSeconds": 35.70227545799571, "environmentStepsPerSecond": 24895.66809392093, "learningRate": 0.00021562499999999997, "loss": 144.23867082595825, "policyLoss": -0.00012743688421323895, "valueLoss": 288.50092601776123, "entropy": 1.1666609048843384, "approximateKl": 0.00011881763566634618, "clipFraction": 0.0, "explainedVariance": 0.017411775111563332, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 11224, "recentEpisodeCount": 100, "recentReturnMean": 103.32625235756201, "recentReturnMedian": 125.75047884289779, "recentLengthMean": 78.51, "recentLandingRate": 0.89 }, { "update": 218, "trainingStep": 892928, "elapsedSeconds": 35.86478933299077, "environmentStepsPerSecond": 24897.06524439631, "learningRate": 0.000215234375, "loss": 152.44189929962158, "policyLoss": -0.0001629119215067476, "valueLoss": 304.90750312805176, "entropy": 1.1688549220561981, "approximateKl": 4.4281357986619696e-05, "clipFraction": 0.0, "explainedVariance": 0.019913083520405217, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 11279, "recentEpisodeCount": 100, "recentReturnMean": 105.91995921630802, "recentReturnMedian": 126.53052627283614, "recentLengthMean": 74.84, "recentLandingRate": 0.9 }, { "update": 219, "trainingStep": 897024, "elapsedSeconds": 36.03136862500105, "environmentStepsPerSecond": 24895.64049969456, "learningRate": 0.00021484374999999995, "loss": 147.69556379318237, "policyLoss": -0.00036728792474605143, "valueLoss": 295.4151201248169, "entropy": 1.1630104333162308, "approximateKl": 6.553753701155074e-05, "clipFraction": 0.0, "explainedVariance": 0.01964678825743138, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 11333, "recentEpisodeCount": 100, "recentReturnMean": 105.85790925991051, "recentReturnMedian": 126.60938899157918, "recentLengthMean": 77.23, "recentLandingRate": 0.9 }, { "update": 220, "trainingStep": 901120, "elapsedSeconds": 36.20905949998996, "environmentStepsPerSecond": 24886.58950117856, "learningRate": 0.000214453125, "loss": 116.29113435745239, "policyLoss": -0.00016833850531838834, "valueLoss": 232.6057996749878, "entropy": 1.15967358648777, "approximateKl": 9.980617687688209e-05, "clipFraction": 0.0, "explainedVariance": 0.017761550420057337, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 11383, "recentEpisodeCount": 100, "recentReturnMean": 108.12555270224199, "recentReturnMedian": 126.70425603655167, "recentLengthMean": 72.1, "recentLandingRate": 0.91 }, { "update": 221, "trainingStep": 905216, "elapsedSeconds": 36.38737054099329, "environmentStepsPerSecond": 24877.202901490276, "learningRate": 0.0002140625, "loss": 108.86262369155884, "policyLoss": -0.00031173926254268736, "valueLoss": 217.74883365631104, "entropy": 1.1481804102659225, "approximateKl": 0.00011227059076190926, "clipFraction": 0.0, "explainedVariance": 0.02184369259444996, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 11431, "recentEpisodeCount": 100, "recentReturnMean": 110.86058103839983, "recentReturnMedian": 127.01595442602411, "recentLengthMean": 80.64, "recentLandingRate": 0.92 }, { "update": 222, "trainingStep": 909312, "elapsedSeconds": 36.55569845798891, "environmentStepsPerSecond": 24874.699112780276, "learningRate": 0.00021367187499999997, "loss": 125.54052114486694, "policyLoss": -0.0006373586365953088, "valueLoss": 251.10565948486328, "entropy": 1.1671623215079308, "approximateKl": 0.0005250642971077468, "clipFraction": 6.103515625e-05, "explainedVariance": 0.023745650402896556, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 11484, "recentEpisodeCount": 100, "recentReturnMean": 110.66479903471831, "recentReturnMedian": 126.94677440088708, "recentLengthMean": 84.3, "recentLandingRate": 0.92 }, { "update": 223, "trainingStep": 913408, "elapsedSeconds": 36.72102274998906, "environmentStepsPerSecond": 24874.252719452703, "learningRate": 0.00021328124999999998, "loss": 165.6192808151245, "policyLoss": -0.0003823259030468762, "valueLoss": 331.2626075744629, "entropy": 1.164309285581112, "approximateKl": 0.00015081204401212744, "clipFraction": 0.0, "explainedVariance": 0.01380685566969475, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 11541, "recentEpisodeCount": 100, "recentReturnMean": 102.03693586704146, "recentReturnMedian": 127.07996519998414, "recentLengthMean": 78.83, "recentLandingRate": 0.88 }, { "update": 224, "trainingStep": 917504, "elapsedSeconds": 36.88015745798475, "environmentStepsPerSecond": 24877.984890526965, "learningRate": 0.000212890625, "loss": 186.3884744644165, "policyLoss": -0.000623562402324751, "valueLoss": 372.8014621734619, "entropy": 1.163270227611065, "approximateKl": 0.0004577395011438057, "clipFraction": 0.0, "explainedVariance": 0.010528721986514555, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 11599, "recentEpisodeCount": 100, "recentReturnMean": 99.7334987499486, "recentReturnMedian": 126.42539294756716, "recentLengthMean": 74.3, "recentLandingRate": 0.87 }, { "update": 225, "trainingStep": 921600, "elapsedSeconds": 37.04497791599715, "environmentStepsPerSecond": 24877.86609266745, "learningRate": 0.00021249999999999996, "loss": 119.06350660324097, "policyLoss": -0.000701995799317956, "valueLoss": 238.15193462371826, "entropy": 1.1757229417562485, "approximateKl": 0.0008105738415906671, "clipFraction": 0.0, "explainedVariance": 0.038786042481138816, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 11655, "recentEpisodeCount": 100, "recentReturnMean": 103.79203635333393, "recentReturnMedian": 126.22101089777425, "recentLengthMean": 72.29, "recentLandingRate": 0.89 }, { "update": 226, "trainingStep": 925696, "elapsedSeconds": 37.20845120798913, "environmentStepsPerSecond": 24878.64906887716, "learningRate": 0.00021210937499999998, "loss": 128.614399433136, "policyLoss": -0.0005819056532345712, "valueLoss": 257.25313663482666, "entropy": 1.1585957258939743, "approximateKl": 0.0003348709433339536, "clipFraction": 0.0, "explainedVariance": 0.03209038916106921, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 11706, "recentEpisodeCount": 100, "recentReturnMean": 110.18681773290068, "recentReturnMedian": 126.69306506123394, "recentLengthMean": 73.13, "recentLandingRate": 0.92 }, { "update": 227, "trainingStep": 929792, "elapsedSeconds": 37.36928637497476, "environmentStepsPerSecond": 24881.181585063863, "learningRate": 0.00021171875, "loss": 162.36929893493652, "policyLoss": -0.00015683018136769533, "valueLoss": 324.76217460632324, "entropy": 1.1632267907261848, "approximateKl": 6.97395189490635e-05, "clipFraction": 0.0, "explainedVariance": 0.0263396260318165, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 11766, "recentEpisodeCount": 100, "recentReturnMean": 103.38770742749503, "recentReturnMedian": 126.42164846049855, "recentLengthMean": 73.68, "recentLandingRate": 0.89 }, { "update": 228, "trainingStep": 933888, "elapsedSeconds": 37.52936629098258, "environmentStepsPerSecond": 24884.193161140352, "learningRate": 0.00021132812499999995, "loss": 140.13422632217407, "policyLoss": -0.00101920694578439, "valueLoss": 280.29370403289795, "entropy": 1.1606372147798538, "approximateKl": 0.0008833120336930733, "clipFraction": 0.0006103515625, "explainedVariance": 0.03192172299622398, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 11824, "recentEpisodeCount": 100, "recentReturnMean": 105.94851387212934, "recentReturnMedian": 126.73938190453919, "recentLengthMean": 70.73, "recentLandingRate": 0.9 }, { "update": 229, "trainingStep": 937984, "elapsedSeconds": 37.69000370797585, "environmentStepsPerSecond": 24886.81102998954, "learningRate": 0.00021093749999999997, "loss": 82.72077655792236, "policyLoss": -0.000640681479126215, "valueLoss": 165.46598148345947, "entropy": 1.157393455505371, "approximateKl": 0.0007219715444080066, "clipFraction": 6.103515625e-05, "explainedVariance": 0.046250956864807846, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 11877, "recentEpisodeCount": 100, "recentReturnMean": 120.33097357591127, "recentReturnMedian": 126.46616017592896, "recentLengthMean": 69.94, "recentLandingRate": 0.97 }, { "update": 230, "trainingStep": 942080, "elapsedSeconds": 37.85124683298636, "environmentStepsPerSecond": 24889.00839004865, "learningRate": 0.000210546875, "loss": 117.56536674499512, "policyLoss": -6.753677735105157e-05, "valueLoss": 235.15393924713135, "entropy": 1.1534981355071068, "approximateKl": 7.071157597238198e-05, "clipFraction": 0.0, "explainedVariance": 0.027738549371518317, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 11933, "recentEpisodeCount": 100, "recentReturnMean": 117.84572492746119, "recentReturnMedian": 125.92637584439944, "recentLengthMean": 75.34, "recentLandingRate": 0.96 }, { "update": 231, "trainingStep": 946176, "elapsedSeconds": 38.01983179099625, "environmentStepsPerSecond": 24886.380486935, "learningRate": 0.00021015624999999995, "loss": 172.60381317138672, "policyLoss": -0.0011539137631189078, "valueLoss": 345.2331943511963, "entropy": 1.162995733320713, "approximateKl": 0.001217808519868413, "clipFraction": 0.00494384765625, "explainedVariance": 0.011959777855339304, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 11991, "recentEpisodeCount": 100, "recentReturnMean": 101.46591998972944, "recentReturnMedian": 125.88788428227417, "recentLengthMean": 73.9, "recentLandingRate": 0.88 }, { "update": 232, "trainingStep": 950272, "elapsedSeconds": 38.17918245799956, "environmentStepsPerSecond": 24889.794354433398, "learningRate": 0.000209765625, "loss": 140.81851387023926, "policyLoss": -9.349663741886616e-05, "valueLoss": 281.6604995727539, "entropy": 1.1641214564442635, "approximateKl": 6.856008985778317e-05, "clipFraction": 0.0, "explainedVariance": 0.037319449894006596, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 12051, "recentEpisodeCount": 100, "recentReturnMean": 99.61668516705205, "recentReturnMedian": 126.34405068703927, "recentLengthMean": 70.22, "recentLandingRate": 0.87 }, { "update": 233, "trainingStep": 954368, "elapsedSeconds": 38.345143415994244, "environmentStepsPerSecond": 24888.88852615221, "learningRate": 0.000209375, "loss": 121.84000444412231, "policyLoss": -0.0006421647849492729, "valueLoss": 243.7044382095337, "entropy": 1.1573255807161331, "approximateKl": 0.0007102528361428995, "clipFraction": 0.00042724609375, "explainedVariance": 0.027035999007322786, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 12107, "recentEpisodeCount": 100, "recentReturnMean": 110.80511318774428, "recentReturnMedian": 127.23475191742182, "recentLengthMean": 69.88, "recentLandingRate": 0.92 }, { "update": 234, "trainingStep": 958464, "elapsedSeconds": 38.518372833001195, "environmentStepsPerSecond": 24883.29411409668, "learningRate": 0.00020898437499999997, "loss": 155.1127152442932, "policyLoss": -0.00030153917032293975, "valueLoss": 310.2491216659546, "entropy": 1.154381699860096, "approximateKl": 0.0002518634282751009, "clipFraction": 0.0, "explainedVariance": 0.014955988506566875, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 12166, "recentEpisodeCount": 100, "recentReturnMean": 102.34287435888895, "recentReturnMedian": 126.88093061430845, "recentLengthMean": 70.24, "recentLandingRate": 0.88 }, { "update": 235, "trainingStep": 962560, "elapsedSeconds": 38.681004040990956, "environmentStepsPerSecond": 24884.56605159364, "learningRate": 0.00020859374999999998, "loss": 124.74261713027954, "policyLoss": -0.0003100743633694947, "valueLoss": 249.50886344909668, "entropy": 1.15042544901371, "approximateKl": 0.0001384722490911372, "clipFraction": 0.0, "explainedVariance": 0.047210272016451116, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 12227, "recentEpisodeCount": 100, "recentReturnMean": 112.76266352072882, "recentReturnMedian": 127.0843380568549, "recentLengthMean": 70.3, "recentLandingRate": 0.93 }, { "update": 236, "trainingStep": 966656, "elapsedSeconds": 38.843869249976706, "environmentStepsPerSecond": 24885.677422585282, "learningRate": 0.000208203125, "loss": 149.14715194702148, "policyLoss": -0.0006304216949502006, "valueLoss": 298.3185205459595, "entropy": 1.1479387432336807, "approximateKl": 0.0003741504260688089, "clipFraction": 0.0, "explainedVariance": 0.014796388845434993, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 12280, "recentEpisodeCount": 100, "recentReturnMean": 106.76774294900432, "recentReturnMedian": 127.36632593686227, "recentLengthMean": 69.4, "recentLandingRate": 0.9 }, { "update": 237, "trainingStep": 970752, "elapsedSeconds": 39.08149337497889, "environmentStepsPerSecond": 24839.17363867942, "learningRate": 0.00020781249999999996, "loss": 138.7610845565796, "policyLoss": -0.0002470018225722015, "valueLoss": 277.5457515716553, "entropy": 1.154366061091423, "approximateKl": 0.00018083755276165903, "clipFraction": 0.0, "explainedVariance": 0.019388723533185992, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 12336, "recentEpisodeCount": 100, "recentReturnMean": 101.62104458969873, "recentReturnMedian": 126.13499197429337, "recentLengthMean": 73.63, "recentLandingRate": 0.88 }, { "update": 238, "trainingStep": 974848, "elapsedSeconds": 39.25128754097386, "environmentStepsPerSecond": 24836.077007215878, "learningRate": 0.00020742187499999998, "loss": 127.84005212783813, "policyLoss": -0.001236946089193225, "valueLoss": 255.7057056427002, "entropy": 1.156443051993847, "approximateKl": 0.0008438324402959552, "clipFraction": 0.0003662109375, "explainedVariance": 0.028169318405987576, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 12392, "recentEpisodeCount": 100, "recentReturnMean": 103.70075986243232, "recentReturnMedian": 126.19430465530604, "recentLengthMean": 74.15, "recentLandingRate": 0.89 }, { "update": 239, "trainingStep": 978944, "elapsedSeconds": 39.41353570797946, "environmentStepsPerSecond": 24837.761505416223, "learningRate": 0.00020703125, "loss": 129.4324245452881, "policyLoss": -0.00031929985561873764, "valueLoss": 258.88853645324707, "entropy": 1.1524454280734062, "approximateKl": 0.0003177668077114504, "clipFraction": 0.0, "explainedVariance": 0.030802504030922884, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 12447, "recentEpisodeCount": 100, "recentReturnMean": 106.20451130226924, "recentReturnMedian": 126.36699150304776, "recentLengthMean": 74.42, "recentLandingRate": 0.9 }, { "update": 240, "trainingStep": 983040, "elapsedSeconds": 39.713119207997806, "environmentStepsPerSecond": 24753.53282756057, "learningRate": 0.00020664062499999996, "loss": 108.85073566436768, "policyLoss": -8.809874998405576e-05, "valueLoss": 217.72467136383057, "entropy": 1.151173748075962, "approximateKl": 7.120859299902804e-05, "clipFraction": 0.0, "explainedVariance": 0.04735642509201088, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 12505, "recentEpisodeCount": 100, "recentReturnMean": 114.7537732037928, "recentReturnMedian": 127.01083529111929, "recentLengthMean": 73.04, "recentLandingRate": 0.94 }, { "update": 241, "trainingStep": 987136, "elapsedSeconds": 39.957900207984494, "environmentStepsPerSecond": 24704.401253866385, "learningRate": 0.00020624999999999997, "loss": 95.28878402709961, "policyLoss": -0.0002802296221489087, "valueLoss": 190.60121536254883, "entropy": 1.1543802246451378, "approximateKl": 6.869920252938755e-05, "clipFraction": 0.0, "explainedVariance": 0.064607441020479, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 12563, "recentEpisodeCount": 100, "recentReturnMean": 118.45758906239425, "recentReturnMedian": 126.69797196937725, "recentLengthMean": 71.99, "recentLandingRate": 0.96 }, { "update": 242, "trainingStep": 991232, "elapsedSeconds": 40.13172212499194, "environmentStepsPerSecond": 24699.463355017913, "learningRate": 0.00020585937500000001, "loss": 101.63909149169922, "policyLoss": -0.0004973296890966594, "valueLoss": 203.3024082183838, "entropy": 1.161431610584259, "approximateKl": 0.00020546478117466904, "clipFraction": 0.0, "explainedVariance": 0.059220733262138614, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 12622, "recentEpisodeCount": 100, "recentReturnMean": 120.90390434817338, "recentReturnMedian": 127.62487540906295, "recentLengthMean": 70.4, "recentLandingRate": 0.97 }, { "update": 243, "trainingStep": 995328, "elapsedSeconds": 40.47100304099149, "environmentStepsPerSecond": 24593.608391466634, "learningRate": 0.00020546874999999995, "loss": 84.95225381851196, "policyLoss": -0.00022517208708450198, "valueLoss": 169.9277639389038, "entropy": 1.1402627900242805, "approximateKl": 0.000108877029560972, "clipFraction": 0.0, "explainedVariance": 0.07408054289859178, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 12678, "recentEpisodeCount": 100, "recentReturnMean": 121.35178964011182, "recentReturnMedian": 127.91665614339581, "recentLengthMean": 70.18, "recentLandingRate": 0.97 }, { "update": 244, "trainingStep": 999424, "elapsedSeconds": 40.79274212499149, "environmentStepsPerSecond": 24500.04456522444, "learningRate": 0.000205078125, "loss": 116.71927833557129, "policyLoss": -0.0006057214341126382, "valueLoss": 233.4626922607422, "entropy": 1.1463109627366066, "approximateKl": 0.00026729208912001923, "clipFraction": 0.0, "explainedVariance": 0.033360214500744, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 12736, "recentEpisodeCount": 100, "recentReturnMean": 116.96814840312625, "recentReturnMedian": 127.35305655840784, "recentLengthMean": 70.26, "recentLandingRate": 0.95 }, { "update": 245, "trainingStep": 1003520, "elapsedSeconds": 41.1915642079839, "environmentStepsPerSecond": 24362.26978254674, "learningRate": 0.0002046875, "loss": 85.93839597702026, "policyLoss": -0.0004503392119659111, "valueLoss": 171.9005537033081, "entropy": 1.1431012600660324, "approximateKl": 0.0004535484440566506, "clipFraction": 0.0, "explainedVariance": 0.06615801366197394, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 12793, "recentEpisodeCount": 100, "recentReturnMean": 116.80401659691539, "recentReturnMedian": 127.11470512393862, "recentLengthMean": 69.23, "recentLandingRate": 0.95 }, { "update": 246, "trainingStep": 1007616, "elapsedSeconds": 41.37445687499712, "environmentStepsPerSecond": 24353.576484260982, "learningRate": 0.00020429687499999997, "loss": 114.50528144836426, "policyLoss": -0.0009793819626793265, "valueLoss": 229.03546810150146, "entropy": 1.1472776904702187, "approximateKl": 0.0007408229539578315, "clipFraction": 0.00018310546875, "explainedVariance": 0.03685483875444284, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 12852, "recentEpisodeCount": 100, "recentReturnMean": 115.15294792564477, "recentReturnMedian": 127.46755692741135, "recentLengthMean": 69.97, "recentLandingRate": 0.94 }, { "update": 247, "trainingStep": 1011712, "elapsedSeconds": 41.545446499978425, "environmentStepsPerSecond": 24351.93469398687, "learningRate": 0.00020390624999999999, "loss": 101.89406251907349, "policyLoss": 0.00015437210095115006, "valueLoss": 203.81062412261963, "entropy": 1.1405535116791725, "approximateKl": 0.00010245176599710248, "clipFraction": 0.0, "explainedVariance": 0.05698159891938748, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 12913, "recentEpisodeCount": 100, "recentReturnMean": 117.57212126068785, "recentReturnMedian": 127.56981609998184, "recentLengthMean": 67.08, "recentLandingRate": 0.95 }, { "update": 248, "trainingStep": 1015808, "elapsedSeconds": 41.71011187499971, "environmentStepsPerSecond": 24353.998451125157, "learningRate": 0.000203515625, "loss": 103.85770750045776, "policyLoss": -0.0006669691938441247, "valueLoss": 207.73978328704834, "entropy": 1.1517357379198074, "approximateKl": 0.00015631160204065964, "clipFraction": 0.0, "explainedVariance": 0.04928045630555922, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 12973, "recentEpisodeCount": 100, "recentReturnMean": 114.69160398579501, "recentReturnMedian": 127.4089804473333, "recentLengthMean": 69.49, "recentLandingRate": 0.94 }, { "update": 249, "trainingStep": 1019904, "elapsedSeconds": 41.883109665999655, "environmentStepsPerSecond": 24351.200475163125, "learningRate": 0.00020312499999999996, "loss": 122.61057138442993, "policyLoss": -0.00028009622474201024, "valueLoss": 245.24454593658447, "entropy": 1.1421302556991577, "approximateKl": 0.00012030144353047945, "clipFraction": 0.0, "explainedVariance": 0.026925266386044866, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 13028, "recentEpisodeCount": 100, "recentReturnMean": 110.26693507997268, "recentReturnMedian": 127.53069303929806, "recentLengthMean": 71.82, "recentLandingRate": 0.92 }, { "update": 250, "trainingStep": 1024000, "elapsedSeconds": 42.048271374980686, "environmentStepsPerSecond": 24352.96307113577, "learningRate": 0.00020273437499999998, "loss": 154.3773488998413, "policyLoss": -0.00043468186049722135, "valueLoss": 308.77842712402344, "entropy": 1.1429384127259254, "approximateKl": 0.00030251406496972777, "clipFraction": 0.0, "explainedVariance": 0.02089460950742661, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 13093, "recentEpisodeCount": 100, "recentReturnMean": 108.68582701211243, "recentReturnMedian": 127.43833636981435, "recentLengthMean": 68.6, "recentLandingRate": 0.91 }, { "update": 251, "trainingStep": 1028096, "elapsedSeconds": 42.2176307499758, "environmentStepsPerSecond": 24352.290304699047, "learningRate": 0.00020234375, "loss": 152.06726837158203, "policyLoss": -0.0005124832387082279, "valueLoss": 304.15826416015625, "entropy": 1.1351092159748077, "approximateKl": 0.00045027510714135133, "clipFraction": 0.0, "explainedVariance": 0.0209788000507104, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 13153, "recentEpisodeCount": 100, "recentReturnMean": 102.25323837593213, "recentReturnMedian": 126.87557218037546, "recentLengthMean": 69.93, "recentLandingRate": 0.88 }, { "update": 252, "trainingStep": 1032192, "elapsedSeconds": 42.37825679098023, "environmentStepsPerSecond": 24356.64130997694, "learningRate": 0.00020195312499999996, "loss": 131.3295464515686, "policyLoss": -0.0003725282440427691, "valueLoss": 262.6828098297119, "entropy": 1.148407369852066, "approximateKl": 0.0004279867425793782, "clipFraction": 0.0, "explainedVariance": 0.04200578270673283, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 13214, "recentEpisodeCount": 100, "recentReturnMean": 110.87506282618153, "recentReturnMedian": 127.1042764527956, "recentLengthMean": 68.32, "recentLandingRate": 0.92 }, { "update": 253, "trainingStep": 1036288, "elapsedSeconds": 42.53469304100145, "environmentStepsPerSecond": 24363.35908198672, "learningRate": 0.00020156249999999997, "loss": 94.29163599014282, "policyLoss": -0.00031061221670825034, "valueLoss": 188.6067409515381, "entropy": 1.1423488333821297, "approximateKl": 4.8081859858939424e-05, "clipFraction": 0.0, "explainedVariance": 0.06688142717719092, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 13277, "recentEpisodeCount": 100, "recentReturnMean": 115.1596950272206, "recentReturnMedian": 127.21453181214747, "recentLengthMean": 65.59, "recentLandingRate": 0.94 }, { "update": 254, "trainingStep": 1040384, "elapsedSeconds": 42.694994874997064, "environmentStepsPerSecond": 24367.82117074962, "learningRate": 0.00020117187500000002, "loss": 129.3619885444641, "policyLoss": -0.0009286124841310084, "valueLoss": 258.74850940704346, "entropy": 1.1337085664272308, "approximateKl": 0.0005841791899001691, "clipFraction": 0.0001220703125, "explainedVariance": 0.036076200524135404, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 13339, "recentEpisodeCount": 100, "recentReturnMean": 112.91720352432156, "recentReturnMedian": 127.58422420162242, "recentLengthMean": 67.27, "recentLandingRate": 0.93 }, { "update": 255, "trainingStep": 1044480, "elapsedSeconds": 42.85211520799203, "environmentStepsPerSecond": 24374.05936510695, "learningRate": 0.00020078124999999995, "loss": 132.05381774902344, "policyLoss": -0.00010938584455288947, "valueLoss": 264.13084983825684, "entropy": 1.1496708020567894, "approximateKl": 0.0005505021945282351, "clipFraction": 0.0, "explainedVariance": 0.04616511565536785, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 13403, "recentEpisodeCount": 100, "recentReturnMean": 111.19479389071971, "recentReturnMedian": 127.66248173464555, "recentLengthMean": 63.85, "recentLandingRate": 0.92 }, { "update": 256, "trainingStep": 1048576, "elapsedSeconds": 43.01183762497385, "environmentStepsPerSecond": 24378.777050696575, "learningRate": 0.000200390625, "loss": 82.8465051651001, "policyLoss": -0.00035541498800739646, "valueLoss": 165.71647262573242, "entropy": 1.1375444903969765, "approximateKl": 4.898914630757645e-05, "clipFraction": 0.0, "explainedVariance": 0.08379405175223908, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 13466, "recentEpisodeCount": 100, "recentReturnMean": 119.61046456070424, "recentReturnMedian": 127.93060285819229, "recentLengthMean": 64.97, "recentLandingRate": 0.96 }, { "update": 257, "trainingStep": 1052672, "elapsedSeconds": 43.1686062499939, "environmentStepsPerSecond": 24385.128255099706, "learningRate": 0.0002, "loss": 108.03317022323608, "policyLoss": -0.0005749859847128391, "valueLoss": 216.09014511108398, "entropy": 1.1328798234462738, "approximateKl": 0.0004331250129325781, "clipFraction": 0.0, "explainedVariance": 0.0662335654793541, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 13529, "recentEpisodeCount": 100, "recentReturnMean": 117.61161151065473, "recentReturnMedian": 127.9584917393513, "recentLengthMean": 68.36, "recentLandingRate": 0.95 }, { "update": 258, "trainingStep": 1056768, "elapsedSeconds": 43.32831545799854, "environmentStepsPerSecond": 24389.778112292555, "learningRate": 0.00019960937499999997, "loss": 90.03803253173828, "policyLoss": -0.0006315915379673243, "valueLoss": 180.0998649597168, "entropy": 1.1269095912575722, "approximateKl": 0.00012800358672393486, "clipFraction": 0.0, "explainedVariance": 0.06832482952081342, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 13589, "recentEpisodeCount": 100, "recentReturnMean": 119.38769976834126, "recentReturnMedian": 127.7683253340656, "recentLengthMean": 66.62, "recentLandingRate": 0.96 }, { "update": 259, "trainingStep": 1060864, "elapsedSeconds": 43.488715082989074, "environmentStepsPerSecond": 24394.006536536293, "learningRate": 0.00019921875, "loss": 143.64815950393677, "policyLoss": -0.00015903374878689647, "valueLoss": 287.31938648223877, "entropy": 1.1371875926852226, "approximateKl": 2.9152051865821704e-05, "clipFraction": 0.0, "explainedVariance": 0.03526716736282076, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 13657, "recentEpisodeCount": 100, "recentReturnMean": 107.89940945097479, "recentReturnMedian": 126.29919479589444, "recentLengthMean": 64.51, "recentLandingRate": 0.91 }, { "update": 260, "trainingStep": 1064960, "elapsedSeconds": 43.64533066598233, "environmentStepsPerSecond": 24400.319203676972, "learningRate": 0.000198828125, "loss": 101.77319240570068, "policyLoss": -0.0002669086679816246, "valueLoss": 203.5696849822998, "entropy": 1.138375997543335, "approximateKl": 3.993549398728646e-05, "clipFraction": 0.0, "explainedVariance": 0.0552084400452042, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 13716, "recentEpisodeCount": 100, "recentReturnMean": 110.71171475801981, "recentReturnMedian": 127.46318197762594, "recentLengthMean": 63.13, "recentLandingRate": 0.92 }, { "update": 261, "trainingStep": 1069056, "elapsedSeconds": 43.80101804097649, "environmentStepsPerSecond": 24407.103939910314, "learningRate": 0.00019843749999999996, "loss": 114.10084056854248, "policyLoss": -0.0002535908715799451, "valueLoss": 228.22491931915283, "entropy": 1.1365167424082756, "approximateKl": 7.206878944998607e-05, "clipFraction": 0.0, "explainedVariance": 0.04424134997533691, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 13778, "recentEpisodeCount": 100, "recentReturnMean": 117.61173551578176, "recentReturnMedian": 128.07615112513304, "recentLengthMean": 65.2, "recentLandingRate": 0.95 }, { "update": 262, "trainingStep": 1073152, "elapsedSeconds": 43.96360354099306, "environmentStepsPerSecond": 24410.009952877474, "learningRate": 0.00019804687499999998, "loss": 97.68248653411865, "policyLoss": -0.000185848941328004, "valueLoss": 195.38793563842773, "entropy": 1.129356473684311, "approximateKl": 7.633891073055565e-05, "clipFraction": 0.0, "explainedVariance": 0.06776573125870766, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 13842, "recentEpisodeCount": 100, "recentReturnMean": 117.80684289741184, "recentReturnMedian": 127.91794051742181, "recentLengthMean": 66.53, "recentLandingRate": 0.95 }, { "update": 263, "trainingStep": 1077248, "elapsedSeconds": 44.12912691599922, "environmentStepsPerSecond": 24411.269274612336, "learningRate": 0.00019765625, "loss": 90.97033977508545, "policyLoss": -0.0003885059559252113, "valueLoss": 181.96401977539062, "entropy": 1.128143072128296, "approximateKl": 0.00023713400878477842, "clipFraction": 0.0, "explainedVariance": 0.06407190209173075, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 13903, "recentEpisodeCount": 100, "recentReturnMean": 121.77613412606966, "recentReturnMedian": 128.1215468616865, "recentLengthMean": 63.67, "recentLandingRate": 0.97 }, { "update": 264, "trainingStep": 1081344, "elapsedSeconds": 44.30464445799589, "environmentStepsPerSecond": 24407.0122495892, "learningRate": 0.00019726562499999996, "loss": 114.1285924911499, "policyLoss": -0.000641614431515336, "valueLoss": 228.28099060058594, "entropy": 1.1260995119810104, "approximateKl": 0.0005868324878974818, "clipFraction": 0.0, "explainedVariance": 0.05623229567050314, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 13971, "recentEpisodeCount": 100, "recentReturnMean": 115.22712124352921, "recentReturnMedian": 127.5804311435204, "recentLengthMean": 64.94, "recentLandingRate": 0.94 }, { "update": 265, "trainingStep": 1085440, "elapsedSeconds": 44.470474749978166, "environmentStepsPerSecond": 24408.10461553557, "learningRate": 0.00019687499999999997, "loss": 114.23114013671875, "policyLoss": -0.0004176598449703306, "valueLoss": 228.48546981811523, "entropy": 1.1178566440939903, "approximateKl": 0.0001372054757666774, "clipFraction": 0.0, "explainedVariance": 0.04833745827638791, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 14035, "recentEpisodeCount": 100, "recentReturnMean": 117.43964237338113, "recentReturnMedian": 127.75851532374509, "recentLengthMean": 60.66, "recentLandingRate": 0.95 }, { "update": 266, "trainingStep": 1089536, "elapsedSeconds": 44.65397795799072, "environmentStepsPerSecond": 24399.528324777842, "learningRate": 0.00019648437500000002, "loss": 91.46544170379639, "policyLoss": -0.00019525477546267211, "valueLoss": 182.9537115097046, "entropy": 1.121914952993393, "approximateKl": 5.690251782652922e-05, "clipFraction": 0.0, "explainedVariance": 0.07599874360603454, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 14100, "recentEpisodeCount": 100, "recentReturnMean": 117.21844670118777, "recentReturnMedian": 128.06205379404128, "recentLengthMean": 63.59, "recentLandingRate": 0.95 }, { "update": 267, "trainingStep": 1093632, "elapsedSeconds": 44.819187415996566, "environmentStepsPerSecond": 24400.97786354931, "learningRate": 0.00019609374999999995, "loss": 90.16720962524414, "policyLoss": -0.0005030595348216593, "valueLoss": 180.357892036438, "entropy": 1.1234167367219925, "approximateKl": 0.00017495638530817814, "clipFraction": 0.0, "explainedVariance": 0.07744228577552048, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 14165, "recentEpisodeCount": 100, "recentReturnMean": 121.7521521664932, "recentReturnMedian": 128.1763304937631, "recentLengthMean": 64.57, "recentLandingRate": 0.97 }, { "update": 268, "trainingStep": 1097728, "elapsedSeconds": 44.978410124982474, "environmentStepsPerSecond": 24405.66478338651, "learningRate": 0.000195703125, "loss": 114.63322830200195, "policyLoss": -8.045326103456318e-05, "valueLoss": 229.28916931152344, "entropy": 1.127719223499298, "approximateKl": 0.00036606317007681355, "clipFraction": 0.0, "explainedVariance": 0.05023143337315661, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 14231, "recentEpisodeCount": 100, "recentReturnMean": 117.1409166467443, "recentReturnMedian": 127.98679124366026, "recentLengthMean": 63.38, "recentLandingRate": 0.95 }, { "update": 269, "trainingStep": 1101824, "elapsedSeconds": 45.133888790995115, "environmentStepsPerSecond": 24412.343574077986, "learningRate": 0.0001953125, "loss": 97.91458177566528, "policyLoss": -4.56827983725816e-05, "valueLoss": 195.85169410705566, "entropy": 1.1219757944345474, "approximateKl": 3.6552068195305765e-05, "clipFraction": 0.0, "explainedVariance": 0.08312907172668293, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 14297, "recentEpisodeCount": 100, "recentReturnMean": 113.46843246467527, "recentReturnMedian": 128.38562970305793, "recentLengthMean": 61.03, "recentLandingRate": 0.93 }, { "update": 270, "trainingStep": 1105920, "elapsedSeconds": 45.296281916002044, "environmentStepsPerSecond": 24415.24896129071, "learningRate": 0.00019492187499999997, "loss": 116.46598768234253, "policyLoss": -0.00032943557016551495, "valueLoss": 232.95491981506348, "entropy": 1.1145343035459518, "approximateKl": 9.395090455655009e-05, "clipFraction": 0.0, "explainedVariance": 0.05201041415686425, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 14361, "recentEpisodeCount": 100, "recentReturnMean": 115.90033791193913, "recentReturnMedian": 128.69950423389673, "recentLengthMean": 61.37, "recentLandingRate": 0.94 }, { "update": 271, "trainingStep": 1110016, "elapsedSeconds": 45.46297912497539, "environmentStepsPerSecond": 24415.821870111573, "learningRate": 0.00019453125, "loss": 105.49208927154541, "policyLoss": -0.00019064240041188896, "valueLoss": 211.00692749023438, "entropy": 1.1183953434228897, "approximateKl": 6.677234341623262e-05, "clipFraction": 0.0, "explainedVariance": 0.056558288895631637, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 14424, "recentEpisodeCount": 100, "recentReturnMean": 113.41836712006392, "recentReturnMedian": 128.08224908355623, "recentLengthMean": 64.43, "recentLandingRate": 0.93 }, { "update": 272, "trainingStep": 1114112, "elapsedSeconds": 45.62666366598569, "environmentStepsPerSecond": 24418.00277478017, "learningRate": 0.000194140625, "loss": 112.53499221801758, "policyLoss": -0.00026961398543789983, "valueLoss": 225.09301662445068, "entropy": 1.1246926337480545, "approximateKl": 1.7566944734426215e-05, "clipFraction": 0.0, "explainedVariance": 0.05367803520603376, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 14490, "recentEpisodeCount": 100, "recentReturnMean": 115.29145122120099, "recentReturnMedian": 127.69641522876918, "recentLengthMean": 62.91, "recentLandingRate": 0.94 }, { "update": 273, "trainingStep": 1118208, "elapsedSeconds": 45.793235790973995, "environmentStepsPerSecond": 24418.628225009656, "learningRate": 0.00019374999999999997, "loss": 107.46743822097778, "policyLoss": -0.0004985073464922607, "valueLoss": 214.95818519592285, "entropy": 1.1156343594193459, "approximateKl": 0.00012667358532780781, "clipFraction": 0.0, "explainedVariance": 0.0481207419719939, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 14548, "recentEpisodeCount": 100, "recentReturnMean": 111.41259969683219, "recentReturnMedian": 127.96303288266063, "recentLengthMean": 62.72, "recentLandingRate": 0.92 }, { "update": 274, "trainingStep": 1122304, "elapsedSeconds": 45.95952687499812, "environmentStepsPerSecond": 24419.39846448965, "learningRate": 0.00019335937499999998, "loss": 72.58449339866638, "policyLoss": -0.00016068757395260036, "valueLoss": 145.19143533706665, "entropy": 1.106208510696888, "approximateKl": 6.31893562967889e-05, "clipFraction": 0.0, "explainedVariance": 0.12127122371517118, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 14616, "recentEpisodeCount": 100, "recentReturnMean": 117.68748447874837, "recentReturnMedian": 128.2291339833755, "recentLengthMean": 66.29, "recentLandingRate": 0.95 }, { "update": 275, "trainingStep": 1126400, "elapsedSeconds": 46.12559650000185, "environmentStepsPerSecond": 24420.280396806465, "learningRate": 0.00019296875, "loss": 99.30766582489014, "policyLoss": -9.993345884140581e-05, "valueLoss": 198.63756275177002, "entropy": 1.1014172583818436, "approximateKl": 2.115284587489441e-05, "clipFraction": 0.0, "explainedVariance": 0.07265525605342349, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 14681, "recentEpisodeCount": 100, "recentReturnMean": 119.33326377676605, "recentReturnMedian": 127.97871985496022, "recentLengthMean": 65.96, "recentLandingRate": 0.96 }, { "update": 276, "trainingStep": 1130496, "elapsedSeconds": 46.36819483299041, "environmentStepsPerSecond": 24380.84993543173, "learningRate": 0.00019257812499999996, "loss": 86.79543256759644, "policyLoss": -0.001054757391102612, "valueLoss": 173.61498546600342, "entropy": 1.1006607413291931, "approximateKl": 0.00031544313969789073, "clipFraction": 0.0, "explainedVariance": 0.10247999684579101, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 14748, "recentEpisodeCount": 100, "recentReturnMean": 117.35679188759197, "recentReturnMedian": 127.83647387352539, "recentLengthMean": 62.8, "recentLandingRate": 0.95 }, { "update": 277, "trainingStep": 1134592, "elapsedSeconds": 46.5453298749926, "environmentStepsPerSecond": 24376.065290485392, "learningRate": 0.00019218749999999998, "loss": 109.07086563110352, "policyLoss": -0.00010837876470759511, "valueLoss": 218.16417026519775, "entropy": 1.111096665263176, "approximateKl": 8.373585296794772e-05, "clipFraction": 0.0, "explainedVariance": 0.059887478304434416, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 14811, "recentEpisodeCount": 100, "recentReturnMean": 115.13364995825235, "recentReturnMedian": 127.32146340608597, "recentLengthMean": 63.79, "recentLandingRate": 0.94 }, { "update": 278, "trainingStep": 1138688, "elapsedSeconds": 46.72334554098779, "environmentStepsPerSecond": 24370.85758341282, "learningRate": 0.00019179687500000002, "loss": 70.90437602996826, "policyLoss": -0.0005632699467241764, "valueLoss": 141.83209085464478, "entropy": 1.1105939894914627, "approximateKl": 0.0002873892954085022, "clipFraction": 0.0, "explainedVariance": 0.14326294793185257, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 14878, "recentEpisodeCount": 100, "recentReturnMean": 122.00060836993595, "recentReturnMedian": 127.99797362962272, "recentLengthMean": 64.41, "recentLandingRate": 0.97 }, { "update": 279, "trainingStep": 1142784, "elapsedSeconds": 46.89060979097849, "environmentStepsPerSecond": 24371.276148766694, "learningRate": 0.00019140624999999995, "loss": 91.81065845489502, "policyLoss": -0.00012500601587817073, "valueLoss": 183.6437520980835, "entropy": 1.1094985604286194, "approximateKl": 7.905810343800113e-05, "clipFraction": 0.0, "explainedVariance": 0.06831431178876068, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 14937, "recentEpisodeCount": 100, "recentReturnMean": 120.16202371189283, "recentReturnMedian": 128.7138518842985, "recentLengthMean": 64.27, "recentLandingRate": 0.96 }, { "update": 280, "trainingStep": 1146880, "elapsedSeconds": 47.05513691599481, "environmentStepsPerSecond": 24373.10940243289, "learningRate": 0.000191015625, "loss": 145.27198123931885, "policyLoss": -0.0009190824639517814, "valueLoss": 290.5680294036865, "entropy": 1.1115847304463387, "approximateKl": 0.0015999060051399283, "clipFraction": 0.008056640625, "explainedVariance": 0.028885221476994127, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 15000, "recentEpisodeCount": 100, "recentReturnMean": 111.06174313175462, "recentReturnMedian": 127.49598298128694, "recentLengthMean": 63.97, "recentLandingRate": 0.92 }, { "update": 281, "trainingStep": 1150976, "elapsedSeconds": 47.22459966599126, "environmentStepsPerSecond": 24372.382363018187, "learningRate": 0.000190625, "loss": 113.01573991775513, "policyLoss": -0.00046042682515690103, "valueLoss": 226.05447578430176, "entropy": 1.103799857199192, "approximateKl": 0.0004523368079389911, "clipFraction": 0.0, "explainedVariance": 0.0619839609325078, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 15072, "recentEpisodeCount": 100, "recentReturnMean": 106.8482394262652, "recentReturnMedian": 127.4641159363091, "recentLengthMean": 60.84, "recentLandingRate": 0.9 }, { "update": 282, "trainingStep": 1155072, "elapsedSeconds": 47.38345870797639, "environmentStepsPerSecond": 24377.114535236717, "learningRate": 0.00019023437499999997, "loss": 60.57745051383972, "policyLoss": -0.0010392928961664438, "valueLoss": 121.179274559021, "entropy": 1.1147546246647835, "approximateKl": 0.0006408734370779712, "clipFraction": 0.0001220703125, "explainedVariance": 0.1852288257907102, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 15139, "recentEpisodeCount": 100, "recentReturnMean": 121.83471035966139, "recentReturnMedian": 128.29517359915917, "recentLengthMean": 62.64, "recentLandingRate": 0.97 }, { "update": 283, "trainingStep": 1159168, "elapsedSeconds": 47.55074391598464, "environmentStepsPerSecond": 24377.494536112496, "learningRate": 0.00018984375, "loss": 110.73707294464111, "policyLoss": -0.00010846587247215211, "valueLoss": 221.49683475494385, "entropy": 1.1235118955373764, "approximateKl": 0.00020999911430408247, "clipFraction": 0.0, "explainedVariance": 0.05695016583066148, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 15203, "recentEpisodeCount": 100, "recentReturnMean": 117.75723354787806, "recentReturnMedian": 128.15031186607666, "recentLengthMean": 61.72, "recentLandingRate": 0.95 }, { "update": 284, "trainingStep": 1163264, "elapsedSeconds": 47.7140493329789, "environmentStepsPerSecond": 24379.905211607715, "learningRate": 0.000189453125, "loss": 158.26892566680908, "policyLoss": -0.0011049642926082015, "valueLoss": 316.5622158050537, "entropy": 1.1076928526163101, "approximateKl": 0.0017095834409701638, "clipFraction": 0.01190185546875, "explainedVariance": 0.03616668160649694, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 15269, "recentEpisodeCount": 100, "recentReturnMean": 110.92940710945804, "recentReturnMedian": 127.43737437902018, "recentLengthMean": 61.54, "recentLandingRate": 0.92 }, { "update": 285, "trainingStep": 1167360, "elapsedSeconds": 47.873677083000075, "environmentStepsPerSecond": 24384.172495797888, "learningRate": 0.00018906249999999997, "loss": 70.55090856552124, "policyLoss": -0.000420056632719934, "valueLoss": 141.12459659576416, "entropy": 1.0969776660203934, "approximateKl": 0.0007615606700710487, "clipFraction": 6.103515625e-05, "explainedVariance": 0.13493862136500612, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 15336, "recentEpisodeCount": 100, "recentReturnMean": 119.7944892020783, "recentReturnMedian": 128.11772187924362, "recentLengthMean": 59.7, "recentLandingRate": 0.96 }, { "update": 286, "trainingStep": 1171456, "elapsedSeconds": 48.03235699998913, "environmentStepsPerSecond": 24388.892679163444, "learningRate": 0.00018867187499999998, "loss": 94.15347862243652, "policyLoss": -0.00036316440673545003, "valueLoss": 188.33007526397705, "entropy": 1.11954927444458, "approximateKl": 6.835759995738044e-05, "clipFraction": 0.0, "explainedVariance": 0.07836707874446136, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 15401, "recentEpisodeCount": 100, "recentReturnMean": 119.59747384055692, "recentReturnMedian": 128.21156392496778, "recentLengthMean": 60.92, "recentLandingRate": 0.96 }, { "update": 287, "trainingStep": 1175552, "elapsedSeconds": 48.18842304099235, "environmentStepsPerSecond": 24394.904954660906, "learningRate": 0.00018828125, "loss": 96.10490703582764, "policyLoss": -0.0004719553398899734, "valueLoss": 192.23281288146973, "entropy": 1.1027275919914246, "approximateKl": 0.0001829410575737711, "clipFraction": 0.0, "explainedVariance": 0.08286996515660994, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 15469, "recentEpisodeCount": 100, "recentReturnMean": 117.67262759615681, "recentReturnMedian": 127.93573465524241, "recentLengthMean": 61.07, "recentLandingRate": 0.95 }, { "update": 288, "trainingStep": 1179648, "elapsedSeconds": 48.35061024999595, "environmentStepsPerSecond": 24397.78927092443, "learningRate": 0.00018789062499999996, "loss": 76.53159403800964, "policyLoss": -0.00028225577261764556, "valueLoss": 153.08565759658813, "entropy": 1.0952856987714767, "approximateKl": 0.00010228799874312244, "clipFraction": 0.0, "explainedVariance": 0.10250066175188932, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 15534, "recentEpisodeCount": 100, "recentReturnMean": 120.18912122800116, "recentReturnMedian": 128.54697933560237, "recentLengthMean": 61.49, "recentLandingRate": 0.96 }, { "update": 289, "trainingStep": 1183744, "elapsedSeconds": 48.508515624998836, "environmentStepsPerSecond": 24402.808140968104, "learningRate": 0.00018749999999999998, "loss": 79.94265270233154, "policyLoss": -0.0004792942781932652, "valueLoss": 159.90839099884033, "entropy": 1.106425054371357, "approximateKl": 0.0001864715559349861, "clipFraction": 0.0, "explainedVariance": 0.08890154758695945, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 15603, "recentEpisodeCount": 100, "recentReturnMean": 121.89064314014337, "recentReturnMedian": 128.40761142177507, "recentLengthMean": 63.8, "recentLandingRate": 0.97 }, { "update": 290, "trainingStep": 1187840, "elapsedSeconds": 48.66586199999438, "environmentStepsPerSecond": 24408.074802006737, "learningRate": 0.000187109375, "loss": 90.13643717765808, "policyLoss": -0.0006855994870420545, "valueLoss": 180.29654121398926, "entropy": 1.1146687120199203, "approximateKl": 0.00021942490639048629, "clipFraction": 0.0, "explainedVariance": 0.07713197572745689, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 15668, "recentEpisodeCount": 100, "recentReturnMean": 117.92207650507088, "recentReturnMedian": 128.53530192153994, "recentLengthMean": 62.53, "recentLandingRate": 0.95 }, { "update": 291, "trainingStep": 1191936, "elapsedSeconds": 48.824514249979984, "environmentStepsPerSecond": 24412.65455089476, "learningRate": 0.00018671874999999995, "loss": 85.26854419708252, "policyLoss": 7.498753257095814e-05, "valueLoss": 170.55906581878662, "entropy": 1.106411173939705, "approximateKl": 2.1697385818697512e-05, "clipFraction": 0.0, "explainedVariance": 0.08774074203377069, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 15734, "recentEpisodeCount": 100, "recentReturnMean": 117.9882465231372, "recentReturnMedian": 128.34807112981798, "recentLengthMean": 62.43, "recentLandingRate": 0.95 }, { "update": 292, "trainingStep": 1196032, "elapsedSeconds": 48.97852774997591, "environmentStepsPerSecond": 24419.517183233183, "learningRate": 0.00018632812499999997, "loss": 102.68798494338989, "policyLoss": -0.0014686580980196595, "valueLoss": 205.40099716186523, "entropy": 1.1045316457748413, "approximateKl": 0.0012636565188586246, "clipFraction": 0.004150390625, "explainedVariance": 0.057312778478439186, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 15796, "recentEpisodeCount": 100, "recentReturnMean": 119.81177073754603, "recentReturnMedian": 128.32917957479367, "recentLengthMean": 61.73, "recentLandingRate": 0.96 }, { "update": 293, "trainingStep": 1200128, "elapsedSeconds": 49.144978415977675, "environmentStepsPerSecond": 24420.15519554736, "learningRate": 0.0001859375, "loss": 89.35454893112183, "policyLoss": 0.00015467879711650312, "valueLoss": 178.73079776763916, "entropy": 1.1003664582967758, "approximateKl": 0.0005836219461343717, "clipFraction": 0.0, "explainedVariance": 0.0940388839068319, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 15868, "recentEpisodeCount": 100, "recentReturnMean": 115.55970075563383, "recentReturnMedian": 128.20033612311818, "recentLengthMean": 61.53, "recentLandingRate": 0.94 }, { "update": 294, "trainingStep": 1204224, "elapsedSeconds": 49.30202354097855, "environmentStepsPerSecond": 24425.44775061982, "learningRate": 0.00018554687499999998, "loss": 105.75121688842773, "policyLoss": -0.0007151910394895822, "valueLoss": 211.5260534286499, "entropy": 1.109442576766014, "approximateKl": 0.00018854668451240286, "clipFraction": 0.0, "explainedVariance": 0.0657877991244672, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 15935, "recentEpisodeCount": 100, "recentReturnMean": 115.89243460137892, "recentReturnMedian": 128.58221790147945, "recentLengthMean": 59.76, "recentLandingRate": 0.94 }, { "update": 295, "trainingStep": 1208320, "elapsedSeconds": 49.45988674997352, "environmentStepsPerSecond": 24430.30260275812, "learningRate": 0.00018515625, "loss": 118.00252532958984, "policyLoss": -0.0005850670568179339, "valueLoss": 236.0282621383667, "entropy": 1.1021154522895813, "approximateKl": 0.0007171168108470738, "clipFraction": 6.103515625e-05, "explainedVariance": 0.05966232350078937, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 16006, "recentEpisodeCount": 100, "recentReturnMean": 115.66247627231496, "recentReturnMedian": 128.4712362793507, "recentLengthMean": 60.04, "recentLandingRate": 0.94 }, { "update": 296, "trainingStep": 1212416, "elapsedSeconds": 49.617833374999464, "environmentStepsPerSecond": 24435.085483012852, "learningRate": 0.000184765625, "loss": 86.3460373878479, "policyLoss": -0.0006754914938937873, "valueLoss": 172.7154483795166, "entropy": 1.1010967120528221, "approximateKl": 0.00047799577805562876, "clipFraction": 0.0, "explainedVariance": 0.0930601175775494, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 16071, "recentEpisodeCount": 100, "recentReturnMean": 119.45298418186896, "recentReturnMedian": 127.46941074822098, "recentLengthMean": 60.09, "recentLandingRate": 0.96 }, { "update": 297, "trainingStep": 1216512, "elapsedSeconds": 49.77402374998201, "environmentStepsPerSecond": 24440.700356286543, "learningRate": 0.00018437499999999997, "loss": 201.52800273895264, "policyLoss": -0.0026387197722215205, "valueLoss": 403.08325958251953, "entropy": 1.0989133939146996, "approximateKl": 0.006058651870262111, "clipFraction": 0.08465576171875, "explainedVariance": 0.02125988355340691, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 16139, "recentEpisodeCount": 100, "recentReturnMean": 100.41428517385357, "recentReturnMedian": 127.24678382067941, "recentLengthMean": 58.35, "recentLandingRate": 0.87 }, { "update": 298, "trainingStep": 1220608, "elapsedSeconds": 49.93691158297588, "environmentStepsPerSecond": 24443.0014053196, "learningRate": 0.00018398437499999998, "loss": 107.61392593383789, "policyLoss": -0.00046640378423035145, "valueLoss": 215.25091361999512, "entropy": 1.1064359545707703, "approximateKl": 0.0005899888419662602, "clipFraction": 6.103515625e-05, "explainedVariance": 0.08625925851989147, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 16210, "recentEpisodeCount": 100, "recentReturnMean": 104.44720668581165, "recentReturnMedian": 127.27598250936717, "recentLengthMean": 57.98, "recentLandingRate": 0.89 }, { "update": 299, "trainingStep": 1224704, "elapsedSeconds": 50.10298812499968, "environmentStepsPerSecond": 24443.73171804726, "learningRate": 0.00018359375, "loss": 101.67617750167847, "policyLoss": -8.273482671938837e-05, "valueLoss": 203.37446975708008, "entropy": 1.0974747613072395, "approximateKl": 6.07707115705125e-05, "clipFraction": 0.0, "explainedVariance": 0.07516393996804904, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 16276, "recentEpisodeCount": 100, "recentReturnMean": 114.99969554054547, "recentReturnMedian": 127.64760210178792, "recentLengthMean": 61.05, "recentLandingRate": 0.94 }, { "update": 300, "trainingStep": 1228800, "elapsedSeconds": 50.28735037500155, "environmentStepsPerSecond": 24435.568603965487, "learningRate": 0.00018320312499999996, "loss": 151.90413665771484, "policyLoss": -0.001024896337185055, "valueLoss": 303.8325004577637, "entropy": 1.1090716198086739, "approximateKl": 0.0006820345261076, "clipFraction": 0.00103759765625, "explainedVariance": 0.04988423779201656, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 16350, "recentEpisodeCount": 100, "recentReturnMean": 106.98465606995276, "recentReturnMedian": 127.52287206752226, "recentLengthMean": 58.08, "recentLandingRate": 0.9 }, { "update": 301, "trainingStep": 1232896, "elapsedSeconds": 50.46544766597799, "environmentStepsPerSecond": 24430.497637915032, "learningRate": 0.00018281249999999998, "loss": 62.970600605010986, "policyLoss": 0.00016526904073543847, "valueLoss": 125.96313190460205, "entropy": 1.112993285059929, "approximateKl": 0.0009132749546552077, "clipFraction": 0.00018310546875, "explainedVariance": 0.17912752132124, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 16418, "recentEpisodeCount": 100, "recentReturnMean": 117.86336304999888, "recentReturnMedian": 128.19438147521578, "recentLengthMean": 58.11, "recentLandingRate": 0.95 }, { "update": 302, "trainingStep": 1236992, "elapsedSeconds": 50.63699654099764, "environmentStepsPerSecond": 24428.62105769808, "learningRate": 0.000182421875, "loss": 132.40274333953857, "policyLoss": -0.0008384585380554199, "valueLoss": 264.8291721343994, "entropy": 1.1003464981913567, "approximateKl": 0.00014650086086476222, "clipFraction": 0.0, "explainedVariance": 0.05978143842746486, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 16491, "recentEpisodeCount": 100, "recentReturnMean": 111.2851095282461, "recentReturnMedian": 128.32190192025155, "recentLengthMean": 57.86, "recentLandingRate": 0.92 }, { "update": 303, "trainingStep": 1241088, "elapsedSeconds": 50.79568762498093, "environmentStepsPerSecond": 24432.940236242466, "learningRate": 0.00018203124999999996, "loss": 71.0817129611969, "policyLoss": -0.0003628019185271114, "valueLoss": 142.1863465309143, "entropy": 1.1096799671649933, "approximateKl": 0.00026670037186704576, "clipFraction": 0.0, "explainedVariance": 0.1266212119855028, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 16560, "recentEpisodeCount": 100, "recentReturnMean": 119.47805750920335, "recentReturnMedian": 128.54421933256526, "recentLengthMean": 58.08, "recentLandingRate": 0.96 }, { "update": 304, "trainingStep": 1245184, "elapsedSeconds": 50.950529624999035, "environmentStepsPerSecond": 24439.078634995123, "learningRate": 0.00018164062499999997, "loss": 98.66072654724121, "policyLoss": -0.00032800319604575634, "valueLoss": 197.34404754638672, "entropy": 1.0969897285103798, "approximateKl": 0.00018998961968463846, "clipFraction": 0.0, "explainedVariance": 0.08574091589897914, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 16627, "recentEpisodeCount": 100, "recentReturnMean": 119.50468706197033, "recentReturnMedian": 128.08174458448775, "recentLengthMean": 58.37, "recentLandingRate": 0.96 }, { "update": 305, "trainingStep": 1249280, "elapsedSeconds": 51.113255874981405, "environmentStepsPerSecond": 24441.409153344302, "learningRate": 0.00018125000000000001, "loss": 117.68636846542358, "policyLoss": -0.0003812723880400881, "valueLoss": 235.3955307006836, "entropy": 1.1016323640942574, "approximateKl": 0.000629586873401422, "clipFraction": 0.0, "explainedVariance": 0.054717019271487644, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 16696, "recentEpisodeCount": 100, "recentReturnMean": 111.161655428909, "recentReturnMedian": 127.58104769932106, "recentLengthMean": 59.15, "recentLandingRate": 0.92 }, { "update": 306, "trainingStep": 1253376, "elapsedSeconds": 51.32928341598017, "environmentStepsPerSecond": 24418.342057153885, "learningRate": 0.00018085937499999995, "loss": 121.28363847732544, "policyLoss": -0.00021271558944135904, "valueLoss": 242.58948230743408, "entropy": 1.0889544188976288, "approximateKl": 0.000126761708088452, "clipFraction": 0.0, "explainedVariance": 0.061019910518126164, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 16769, "recentEpisodeCount": 100, "recentReturnMean": 114.04910721421766, "recentReturnMedian": 128.76746986666694, "recentLengthMean": 58.5, "recentLandingRate": 0.93 }, { "update": 307, "trainingStep": 1257472, "elapsedSeconds": 51.50308799999766, "environmentStepsPerSecond": 24415.468058926042, "learningRate": 0.00018046875, "loss": 77.80939888954163, "policyLoss": -0.00015969923697412014, "valueLoss": 155.64120817184448, "entropy": 1.1045963540673256, "approximateKl": 2.0839728676946834e-05, "clipFraction": 0.0, "explainedVariance": 0.13829067710258924, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 16842, "recentEpisodeCount": 100, "recentReturnMean": 120.24605746331298, "recentReturnMedian": 128.85576812300133, "recentLengthMean": 57.15, "recentLandingRate": 0.96 }, { "update": 308, "trainingStep": 1261568, "elapsedSeconds": 51.666224374988815, "environmentStepsPerSecond": 24417.654188230455, "learningRate": 0.000180078125, "loss": 47.00944232940674, "policyLoss": -8.53156961966306e-05, "valueLoss": 94.0412425994873, "entropy": 1.10938810557127, "approximateKl": 2.9919945518486202e-05, "clipFraction": 0.0, "explainedVariance": 0.2347858295601526, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 16910, "recentEpisodeCount": 100, "recentReturnMean": 124.49048939684893, "recentReturnMedian": 128.54885529261082, "recentLengthMean": 58.44, "recentLandingRate": 0.98 }, { "update": 309, "trainingStep": 1265664, "elapsedSeconds": 51.837191040976904, "environmentStepsPerSecond": 24416.137807303297, "learningRate": 0.00017968749999999997, "loss": 66.28022861480713, "policyLoss": -0.0006210053834365681, "valueLoss": 132.58355712890625, "entropy": 1.0928520187735558, "approximateKl": 6.156726522021927e-05, "clipFraction": 0.0, "explainedVariance": 0.11755328704507384, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 16976, "recentEpisodeCount": 100, "recentReturnMean": 124.44810400921676, "recentReturnMedian": 128.61071783164516, "recentLengthMean": 59.06, "recentLandingRate": 0.98 }, { "update": 310, "trainingStep": 1269760, "elapsedSeconds": 51.99655054099276, "environmentStepsPerSecond": 24420.08146288384, "learningRate": 0.00017929687499999999, "loss": 71.0731291770935, "policyLoss": -0.00010445088264532387, "valueLoss": 142.1686086654663, "entropy": 1.1070122867822647, "approximateKl": 3.7690773751819506e-05, "clipFraction": 0.0, "explainedVariance": 0.11622335448398502, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 17048, "recentEpisodeCount": 100, "recentReturnMean": 124.40953083357192, "recentReturnMedian": 128.6114051855402, "recentLengthMean": 60.19, "recentLandingRate": 0.98 }, { "update": 311, "trainingStep": 1273856, "elapsedSeconds": 52.15016995798214, "environmentStepsPerSecond": 24426.689328651413, "learningRate": 0.00017890625, "loss": 54.657591342926025, "policyLoss": -0.0004184384597465396, "valueLoss": 109.33825063705444, "entropy": 1.1115350425243378, "approximateKl": 0.00012932164099765942, "clipFraction": 0.0, "explainedVariance": 0.16590977461051581, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 17117, "recentEpisodeCount": 100, "recentReturnMean": 124.36248018791244, "recentReturnMedian": 128.4590261382982, "recentLengthMean": 60.8, "recentLandingRate": 0.98 }, { "update": 312, "trainingStep": 1277952, "elapsedSeconds": 52.30880462497589, "environmentStepsPerSecond": 24430.91577339957, "learningRate": 0.00017851562499999996, "loss": 83.05479431152344, "policyLoss": -0.00021116709103807807, "valueLoss": 166.13198041915894, "entropy": 1.0984285175800323, "approximateKl": 0.00011962906864937395, "clipFraction": 0.0, "explainedVariance": 0.09683828840199393, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 17187, "recentEpisodeCount": 100, "recentReturnMean": 122.166621926863, "recentReturnMedian": 128.23677192954347, "recentLengthMean": 59.33, "recentLandingRate": 0.97 }, { "update": 313, "trainingStep": 1282048, "elapsedSeconds": 52.46467874999507, "environmentStepsPerSecond": 24436.40236718538, "learningRate": 0.00017812499999999998, "loss": 55.71593618392944, "policyLoss": -0.00012517163122538477, "valueLoss": 111.45393657684326, "entropy": 1.0906232669949532, "approximateKl": 5.738187610404566e-05, "clipFraction": 0.0, "explainedVariance": 0.1688129557834045, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 17253, "recentEpisodeCount": 100, "recentReturnMean": 124.63283848814957, "recentReturnMedian": 128.24739509960636, "recentLengthMean": 57.91, "recentLandingRate": 0.98 }, { "update": 314, "trainingStep": 1286144, "elapsedSeconds": 52.628873040986946, "environmentStepsPerSecond": 24437.992411472715, "learningRate": 0.000177734375, "loss": 84.04507780075073, "policyLoss": -0.0001849265827331692, "valueLoss": 168.11253452301025, "entropy": 1.100424475967884, "approximateKl": 6.134055365691893e-05, "clipFraction": 0.0, "explainedVariance": 0.0878434751352889, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 17323, "recentEpisodeCount": 100, "recentReturnMean": 122.40238010201838, "recentReturnMedian": 128.87062471313402, "recentLengthMean": 58.5, "recentLandingRate": 0.97 }, { "update": 315, "trainingStep": 1290240, "elapsedSeconds": 52.788916665973375, "environmentStepsPerSecond": 24441.494190231442, "learningRate": 0.00017734374999999996, "loss": 63.393314361572266, "policyLoss": -0.00011415412882342935, "valueLoss": 126.80869340896606, "entropy": 1.091892421245575, "approximateKl": 3.0321130907395855e-05, "clipFraction": 0.0, "explainedVariance": 0.12516438432643562, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 17391, "recentEpisodeCount": 100, "recentReturnMean": 122.25078481349077, "recentReturnMedian": 128.865848046029, "recentLengthMean": 59.74, "recentLandingRate": 0.97 }, { "update": 316, "trainingStep": 1294336, "elapsedSeconds": 52.94352424997487, "environmentStepsPerSecond": 24447.48471765391, "learningRate": 0.00017695312499999997, "loss": 117.7993712425232, "policyLoss": -0.00026121172413695604, "valueLoss": 235.62111282348633, "entropy": 1.0922535732388496, "approximateKl": 4.1548555600456893e-05, "clipFraction": 0.0, "explainedVariance": 0.060449447624961294, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 17467, "recentEpisodeCount": 100, "recentReturnMean": 117.98250007846691, "recentReturnMedian": 128.05317543417914, "recentLengthMean": 57.74, "recentLandingRate": 0.95 }, { "update": 317, "trainingStep": 1298432, "elapsedSeconds": 53.10280924997642, "environmentStepsPerSecond": 24451.286444898895, "learningRate": 0.00017656250000000002, "loss": 143.1246738433838, "policyLoss": -0.0003559394972398877, "valueLoss": 286.2717742919922, "entropy": 1.085637904703617, "approximateKl": 0.0001853593894338701, "clipFraction": 0.0, "explainedVariance": 0.039902639401147466, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 17537, "recentEpisodeCount": 100, "recentReturnMean": 111.5229556508144, "recentReturnMedian": 128.2276569749083, "recentLengthMean": 58.54, "recentLandingRate": 0.92 }, { "update": 318, "trainingStep": 1302528, "elapsedSeconds": 53.256865874980576, "environmentStepsPerSecond": 24457.466255292948, "learningRate": 0.00017617187499999995, "loss": 84.55615663528442, "policyLoss": -0.0005383989191614091, "valueLoss": 169.13529014587402, "entropy": 1.0950801372528076, "approximateKl": 0.00022809539586887695, "clipFraction": 0.0, "explainedVariance": 0.09559661666622987, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 17602, "recentEpisodeCount": 100, "recentReturnMean": 112.07527859124122, "recentReturnMedian": 128.63079157011816, "recentLengthMean": 58.73, "recentLandingRate": 0.92 }, { "update": 319, "trainingStep": 1306624, "elapsedSeconds": 53.41026729097939, "environmentStepsPerSecond": 24463.910522699807, "learningRate": 0.00017578125, "loss": 104.38399505615234, "policyLoss": -0.0004549474106170237, "valueLoss": 208.79076385498047, "entropy": 1.0933417975902557, "approximateKl": 0.0001906644283735659, "clipFraction": 0.0, "explainedVariance": 0.07883815472674327, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 17674, "recentEpisodeCount": 100, "recentReturnMean": 115.69213639190471, "recentReturnMedian": 128.30140620097518, "recentLengthMean": 57.97, "recentLandingRate": 0.94 }, { "update": 320, "trainingStep": 1310720, "elapsedSeconds": 53.56767691599089, "environmentStepsPerSecond": 24468.48688352821, "learningRate": 0.000175390625, "loss": 142.09136581420898, "policyLoss": -0.0007817477016942576, "valueLoss": 284.2062015533447, "entropy": 1.0955166518688202, "approximateKl": 0.0004001613560831174, "clipFraction": 0.0, "explainedVariance": 0.03985417658439916, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 17746, "recentEpisodeCount": 100, "recentReturnMean": 109.40918426528813, "recentReturnMedian": 128.0950988381228, "recentLengthMean": 57.58, "recentLandingRate": 0.91 }, { "update": 321, "trainingStep": 1314816, "elapsedSeconds": 53.722612249985104, "environmentStepsPerSecond": 24474.163577188385, "learningRate": 0.00017499999999999997, "loss": 35.82206583023071, "policyLoss": 9.949639206752181e-05, "valueLoss": 71.66568851470947, "entropy": 1.0878292471170425, "approximateKl": 0.0001465301975258626, "clipFraction": 0.0, "explainedVariance": 0.2895872697400057, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 17812, "recentEpisodeCount": 100, "recentReturnMean": 124.31287198185048, "recentReturnMedian": 128.79485694505274, "recentLengthMean": 59.41, "recentLandingRate": 0.98 }, { "update": 322, "trainingStep": 1318912, "elapsedSeconds": 53.873457999987295, "environmentStepsPerSecond": 24481.66590680537, "learningRate": 0.000174609375, "loss": 47.24880290031433, "policyLoss": -0.0004748752398882061, "valueLoss": 94.52091407775879, "entropy": 1.1179545000195503, "approximateKl": 0.0001562466932227835, "clipFraction": 0.0, "explainedVariance": 0.18517795778075152, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 17879, "recentEpisodeCount": 100, "recentReturnMean": 126.09967758619474, "recentReturnMedian": 128.53110714671493, "recentLengthMean": 60.62, "recentLandingRate": 0.99 }, { "update": 323, "trainingStep": 1323008, "elapsedSeconds": 54.02682774999994, "environmentStepsPerSecond": 24487.98226914223, "learningRate": 0.00017421875, "loss": 80.56056046485901, "policyLoss": -0.00046471095993183553, "valueLoss": 161.14418077468872, "entropy": 1.1065515577793121, "approximateKl": 0.00021063578242319636, "clipFraction": 0.0, "explainedVariance": 0.09126712872588794, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 17949, "recentEpisodeCount": 100, "recentReturnMean": 122.03154875598149, "recentReturnMedian": 128.31555172771914, "recentLengthMean": 60.98, "recentLandingRate": 0.97 }, { "update": 324, "trainingStep": 1327104, "elapsedSeconds": 54.17907566597569, "environmentStepsPerSecond": 24494.770050745214, "learningRate": 0.00017382812499999996, "loss": 65.13537335395813, "policyLoss": -8.314181468449533e-05, "valueLoss": 130.29284191131592, "entropy": 1.0965048670768738, "approximateKl": 0.00013313067393028177, "clipFraction": 0.0, "explainedVariance": 0.13170748893975703, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 18017, "recentEpisodeCount": 100, "recentReturnMean": 122.38995800285353, "recentReturnMedian": 128.9090204279637, "recentLengthMean": 59.43, "recentLandingRate": 0.97 }, { "update": 325, "trainingStep": 1331200, "elapsedSeconds": 54.335344790975796, "environmentStepsPerSecond": 24499.706500824308, "learningRate": 0.00017343749999999998, "loss": 76.91148138046265, "policyLoss": -0.0006550709367729723, "valueLoss": 153.84588813781738, "entropy": 1.0808540657162666, "approximateKl": 0.0002592883065517526, "clipFraction": 0.0, "explainedVariance": 0.09556708450648088, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 18084, "recentEpisodeCount": 100, "recentReturnMean": 120.91033517893702, "recentReturnMedian": 129.66214029258117, "recentLengthMean": 59.78, "recentLandingRate": 0.96 }, { "update": 326, "trainingStep": 1335296, "elapsedSeconds": 54.490072790998966, "environmentStepsPerSecond": 24505.30769378185, "learningRate": 0.000173046875, "loss": 92.75435066223145, "policyLoss": -0.0012783648271579295, "valueLoss": 185.53277349472046, "entropy": 1.075709655880928, "approximateKl": 0.0015732718093204312, "clipFraction": 0.00738525390625, "explainedVariance": 0.08398108156775996, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 18157, "recentEpisodeCount": 100, "recentReturnMean": 117.91483830124947, "recentReturnMedian": 128.53804362844676, "recentLengthMean": 57.87, "recentLandingRate": 0.95 }, { "update": 327, "trainingStep": 1339392, "elapsedSeconds": 54.6464064999891, "environmentStepsPerSecond": 24510.156948751373, "learningRate": 0.00017265624999999996, "loss": 68.75520968437195, "policyLoss": -0.00021005505550419912, "valueLoss": 137.53234195709229, "entropy": 1.0750915259122849, "approximateKl": 8.533904474461451e-05, "clipFraction": 0.0, "explainedVariance": 0.14183944756838585, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 18231, "recentEpisodeCount": 100, "recentReturnMean": 122.4258184781106, "recentReturnMedian": 128.80046979396138, "recentLengthMean": 57.32, "recentLandingRate": 0.97 }, { "update": 328, "trainingStep": 1343488, "elapsedSeconds": 54.80420554097509, "environmentStepsPerSecond": 24514.323065873537, "learningRate": 0.00017226562499999997, "loss": 110.09656238555908, "policyLoss": -0.000303310138406232, "valueLoss": 220.21539402008057, "entropy": 1.0831251963973045, "approximateKl": 8.602214802522212e-05, "clipFraction": 0.0, "explainedVariance": 0.059774198780691346, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 18299, "recentEpisodeCount": 100, "recentReturnMean": 118.46169050264577, "recentReturnMedian": 129.13434691622388, "recentLengthMean": 57.63, "recentLandingRate": 0.95 }, { "update": 329, "trainingStep": 1347584, "elapsedSeconds": 54.96344391599996, "environmentStepsPerSecond": 24517.82319280244, "learningRate": 0.00017187500000000002, "loss": 76.43735194206238, "policyLoss": -0.0010368679068051279, "valueLoss": 152.89840459823608, "entropy": 1.0814044624567032, "approximateKl": 0.00031886088981991634, "clipFraction": 0.0, "explainedVariance": 0.10471595690241142, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 18370, "recentEpisodeCount": 100, "recentReturnMean": 118.23126688401594, "recentReturnMedian": 128.59028300642967, "recentLengthMean": 58.93, "recentLandingRate": 0.95 }, { "update": 330, "trainingStep": 1351680, "elapsedSeconds": 55.12367366597755, "environmentStepsPerSecond": 24520.86209258328, "learningRate": 0.00017148437499999995, "loss": 60.972211837768555, "policyLoss": 5.4875388741493225e-05, "valueLoss": 121.96614360809326, "entropy": 1.091370351612568, "approximateKl": 0.00012639079068321735, "clipFraction": 0.0, "explainedVariance": 0.12517610158795922, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 18436, "recentEpisodeCount": 100, "recentReturnMean": 121.82007373453263, "recentReturnMedian": 127.80461230908986, "recentLengthMean": 60.12, "recentLandingRate": 0.97 }, { "update": 331, "trainingStep": 1355776, "elapsedSeconds": 55.27678395799012, "environmentStepsPerSecond": 24527.041968114103, "learningRate": 0.00017109375, "loss": 47.5579628944397, "policyLoss": -0.0004435201990418136, "valueLoss": 95.13842678070068, "entropy": 1.0807072520256042, "approximateKl": 0.00015015419194241986, "clipFraction": 0.0, "explainedVariance": 0.18307794683788703, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 18502, "recentEpisodeCount": 100, "recentReturnMean": 122.12047966490601, "recentReturnMedian": 128.38982492731884, "recentLengthMean": 59.71, "recentLandingRate": 0.97 }, { "update": 332, "trainingStep": 1359872, "elapsedSeconds": 55.429061290982645, "environmentStepsPerSecond": 24533.556375078424, "learningRate": 0.000170703125, "loss": 49.90115928649902, "policyLoss": -0.0010219700634479523, "valueLoss": 99.82587337493896, "entropy": 1.0756012573838234, "approximateKl": 0.0003838290613202844, "clipFraction": 0.0, "explainedVariance": 0.17966653839581181, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 18572, "recentEpisodeCount": 100, "recentReturnMean": 126.70739071257834, "recentReturnMedian": 129.1602975083515, "recentLengthMean": 58.86, "recentLandingRate": 0.99 }, { "update": 333, "trainingStep": 1363968, "elapsedSeconds": 55.58169962497777, "environmentStepsPerSecond": 24539.87570014949, "learningRate": 0.00017031249999999997, "loss": 81.64139127731323, "policyLoss": -0.0010322261950932443, "valueLoss": 163.30625820159912, "entropy": 1.0706224143505096, "approximateKl": 0.00040569546399638057, "clipFraction": 0.0, "explainedVariance": 0.10613086038124675, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 18652, "recentEpisodeCount": 100, "recentReturnMean": 120.33971229614107, "recentReturnMedian": 128.7615642286837, "recentLengthMean": 57.57, "recentLandingRate": 0.96 }, { "update": 334, "trainingStep": 1368064, "elapsedSeconds": 55.73368816598668, "environmentStepsPerSecond": 24546.4465930483, "learningRate": 0.000169921875, "loss": 83.45934343338013, "policyLoss": -0.0008279814501293004, "valueLoss": 166.94192028045654, "entropy": 1.0790855661034584, "approximateKl": 0.0013461698108585551, "clipFraction": 0.004150390625, "explainedVariance": 0.08980370661973325, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 18718, "recentEpisodeCount": 100, "recentReturnMean": 115.93227198666064, "recentReturnMedian": 128.16804263053928, "recentLengthMean": 57.1, "recentLandingRate": 0.94 }, { "update": 335, "trainingStep": 1372160, "elapsedSeconds": 55.89018570797634, "environmentStepsPerSecond": 24551.0009068403, "learningRate": 0.00016953125, "loss": 50.33216428756714, "policyLoss": 0.00015750550664961338, "valueLoss": 100.68548345565796, "entropy": 1.0734972730278969, "approximateKl": 9.203969239024445e-05, "clipFraction": 0.0, "explainedVariance": 0.2035830772425068, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 18791, "recentEpisodeCount": 100, "recentReturnMean": 120.1553675648477, "recentReturnMedian": 128.63849013741128, "recentLengthMean": 56.51, "recentLandingRate": 0.96 }, { "update": 336, "trainingStep": 1376256, "elapsedSeconds": 56.04436441598227, "environmentStepsPerSecond": 24556.54577121996, "learningRate": 0.00016914062499999997, "loss": 128.06670665740967, "policyLoss": -0.0003634217719081789, "valueLoss": 256.15513801574707, "entropy": 1.0499481484293938, "approximateKl": 0.00013537503400584683, "clipFraction": 0.0, "explainedVariance": 0.05945117586191806, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 18867, "recentEpisodeCount": 100, "recentReturnMean": 115.90988883910832, "recentReturnMedian": 128.8453183239326, "recentLengthMean": 54.8, "recentLandingRate": 0.94 }, { "update": 337, "trainingStep": 1380352, "elapsedSeconds": 56.197670749999816, "environmentStepsPerSecond": 24562.44149585158, "learningRate": 0.00016874999999999998, "loss": 84.91805481910706, "policyLoss": -8.643462206237018e-05, "valueLoss": 169.85773515701294, "entropy": 1.0726520791649818, "approximateKl": 9.892228626995347e-05, "clipFraction": 0.0, "explainedVariance": 0.10621825178751765, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 18943, "recentEpisodeCount": 100, "recentReturnMean": 109.56674660656135, "recentReturnMedian": 128.66136021586135, "recentLengthMean": 55.15, "recentLandingRate": 0.91 }, { "update": 338, "trainingStep": 1384448, "elapsedSeconds": 56.35064583297935, "environmentStepsPerSecond": 24568.44956317694, "learningRate": 0.000168359375, "loss": 92.8986325263977, "policyLoss": -0.0007096055487636477, "valueLoss": 185.82025146484375, "entropy": 1.078379139304161, "approximateKl": 0.0004107184759050142, "clipFraction": 0.0, "explainedVariance": 0.09086639971676425, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 19012, "recentEpisodeCount": 100, "recentReturnMean": 115.96242188410938, "recentReturnMedian": 128.54937684955075, "recentLengthMean": 56.81, "recentLandingRate": 0.94 }, { "update": 339, "trainingStep": 1388544, "elapsedSeconds": 56.50393729098141, "environmentStepsPerSecond": 24574.28750229102, "learningRate": 0.00016796874999999996, "loss": 107.01864910125732, "policyLoss": -0.0007762079767417163, "valueLoss": 214.06024265289307, "entropy": 1.0696038082242012, "approximateKl": 0.00039204495260491967, "clipFraction": 0.0, "explainedVariance": 0.06798507837646195, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 19083, "recentEpisodeCount": 100, "recentReturnMean": 111.68814694695641, "recentReturnMedian": 128.15634297463112, "recentLengthMean": 56.68, "recentLandingRate": 0.92 }, { "update": 340, "trainingStep": 1392640, "elapsedSeconds": 56.66036074998556, "environmentStepsPerSecond": 24578.735143340135, "learningRate": 0.00016757812499999998, "loss": 58.413007497787476, "policyLoss": -0.00019919814076274633, "valueLoss": 116.84762239456177, "entropy": 1.0604616031050682, "approximateKl": 0.000603586740908213, "clipFraction": 0.0, "explainedVariance": 0.17957220266390816, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 19158, "recentEpisodeCount": 100, "recentReturnMean": 122.46090166710746, "recentReturnMedian": 128.85522868391126, "recentLengthMean": 57.37, "recentLandingRate": 0.97 }, { "update": 341, "trainingStep": 1396736, "elapsedSeconds": 56.813807665981585, "environmentStepsPerSecond": 24584.44623552883, "learningRate": 0.00016718750000000002, "loss": 85.25924253463745, "policyLoss": -0.0007187785231508315, "valueLoss": 170.5414800643921, "entropy": 1.0779374316334724, "approximateKl": 0.0004301601366023533, "clipFraction": 6.103515625e-05, "explainedVariance": 0.08479583042158689, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 19222, "recentEpisodeCount": 100, "recentReturnMean": 120.24720330638985, "recentReturnMedian": 128.3826806099387, "recentLengthMean": 56.88, "recentLandingRate": 0.96 }, { "update": 342, "trainingStep": 1400832, "elapsedSeconds": 56.97344858298311, "environmentStepsPerSecond": 24587.453188122476, "learningRate": 0.00016679687499999995, "loss": 57.10476279258728, "policyLoss": -0.001324662720435299, "valueLoss": 114.23358249664307, "entropy": 1.0703168958425522, "approximateKl": 0.0016290783241856843, "clipFraction": 0.00726318359375, "explainedVariance": 0.16071343480507594, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 19296, "recentEpisodeCount": 100, "recentReturnMean": 121.81687557116864, "recentReturnMedian": 128.10524232441094, "recentLengthMean": 57.31, "recentLandingRate": 0.97 }, { "update": 343, "trainingStep": 1404928, "elapsedSeconds": 57.12582641598419, "environmentStepsPerSecond": 24593.569811480076, "learningRate": 0.00016640625, "loss": 91.55280613899231, "policyLoss": -0.0007845869986340404, "valueLoss": 183.12855052947998, "entropy": 1.06845360994339, "approximateKl": 0.00042004659917438403, "clipFraction": 0.00030517578125, "explainedVariance": 0.09121726077275871, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 19370, "recentEpisodeCount": 100, "recentReturnMean": 119.82841981942809, "recentReturnMedian": 128.36579343304038, "recentLengthMean": 56.92, "recentLandingRate": 0.96 }, { "update": 344, "trainingStep": 1409024, "elapsedSeconds": 57.2797733329935, "environmentStepsPerSecond": 24598.980024042685, "learningRate": 0.000166015625, "loss": 79.80938053131104, "policyLoss": -0.0003010676009580493, "valueLoss": 159.64041996002197, "entropy": 1.0529454201459885, "approximateKl": 0.0008363144625036512, "clipFraction": 0.00018310546875, "explainedVariance": 0.12368409149136328, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 19446, "recentEpisodeCount": 100, "recentReturnMean": 113.57726306452038, "recentReturnMedian": 128.26397306937724, "recentLengthMean": 55.96, "recentLandingRate": 0.93 }, { "update": 345, "trainingStep": 1413120, "elapsedSeconds": 57.429633457999444, "environmentStepsPerSecond": 24606.112122123683, "learningRate": 0.00016562499999999997, "loss": 44.75216269493103, "policyLoss": -0.00023599882842972875, "valueLoss": 89.52615261077881, "entropy": 1.0677882134914398, "approximateKl": 3.995607403339818e-05, "clipFraction": 0.0, "explainedVariance": 0.22913282070872343, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 19514, "recentEpisodeCount": 100, "recentReturnMean": 122.56038744911457, "recentReturnMedian": 128.54161304267473, "recentLengthMean": 56.22, "recentLandingRate": 0.97 }, { "update": 346, "trainingStep": 1417216, "elapsedSeconds": 57.58098762499867, "environmentStepsPerSecond": 24612.56846148152, "learningRate": 0.000165234375, "loss": 28.390057802200317, "policyLoss": -0.0002670219982974231, "valueLoss": 56.80216670036316, "entropy": 1.075848065316677, "approximateKl": 6.360874249367043e-05, "clipFraction": 0.0, "explainedVariance": 0.3488437630723391, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 19584, "recentEpisodeCount": 100, "recentReturnMean": 126.44220155731914, "recentReturnMedian": 128.50208928622305, "recentLengthMean": 56.36, "recentLandingRate": 0.99 }, { "update": 347, "trainingStep": 1421312, "elapsedSeconds": 57.735761624993756, "environmentStepsPerSecond": 24617.532704110297, "learningRate": 0.00016484375, "loss": 47.131884932518005, "policyLoss": -0.00047129832091741264, "valueLoss": 94.28607177734375, "entropy": 1.0679980739951134, "approximateKl": 0.00017827165356720798, "clipFraction": 0.0, "explainedVariance": 0.20963416809891589, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 19663, "recentEpisodeCount": 100, "recentReturnMean": 126.02143945508371, "recentReturnMedian": 128.28113907855004, "recentLengthMean": 57.11, "recentLandingRate": 0.99 }, { "update": 348, "trainingStep": 1425408, "elapsedSeconds": 57.90058529097587, "environmentStepsPerSecond": 24618.19673906056, "learningRate": 0.00016445312499999997, "loss": 44.46511936187744, "policyLoss": -0.00031493051210418344, "valueLoss": 88.95221662521362, "entropy": 1.067430131137371, "approximateKl": 0.00011335083399899304, "clipFraction": 0.0, "explainedVariance": 0.1858639273630306, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 19730, "recentEpisodeCount": 100, "recentReturnMean": 126.44556253459683, "recentReturnMedian": 128.7132911523804, "recentLengthMean": 58.09, "recentLandingRate": 0.99 }, { "update": 349, "trainingStep": 1429504, "elapsedSeconds": 58.08680066600209, "environmentStepsPerSecond": 24609.790582539026, "learningRate": 0.00016406249999999998, "loss": 46.52228093147278, "policyLoss": -0.00032059114892035723, "valueLoss": 93.06637668609619, "entropy": 1.0586966425180435, "approximateKl": 0.00012296083878027275, "clipFraction": 0.0, "explainedVariance": 0.1787236970290058, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 19801, "recentEpisodeCount": 100, "recentReturnMean": 124.67610568775879, "recentReturnMedian": 129.13379729213193, "recentLengthMean": 57.57, "recentLandingRate": 0.98 }, { "update": 350, "trainingStep": 1433600, "elapsedSeconds": 58.25627312497818, "environmentStepsPerSecond": 24608.5086308984, "learningRate": 0.000163671875, "loss": 39.060022830963135, "policyLoss": -0.0006046033522579819, "valueLoss": 78.14224004745483, "entropy": 1.0492849126458168, "approximateKl": 0.0001667644246481359, "clipFraction": 0.0, "explainedVariance": 0.25809363841078503, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 19877, "recentEpisodeCount": 100, "recentReturnMean": 125.10412032462307, "recentReturnMedian": 129.39182369271293, "recentLengthMean": 57.24, "recentLandingRate": 0.98 }, { "update": 351, "trainingStep": 1437696, "elapsedSeconds": 58.41549037498771, "environmentStepsPerSecond": 24611.554071890343, "learningRate": 0.00016328124999999996, "loss": 46.29901647567749, "policyLoss": -0.00037967850221320987, "valueLoss": 92.61991882324219, "entropy": 1.0563285872340202, "approximateKl": 0.00011199582149856724, "clipFraction": 0.0, "explainedVariance": 0.20448171576081664, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 19951, "recentEpisodeCount": 100, "recentReturnMean": 126.74073486193898, "recentReturnMedian": 129.1882348060608, "recentLengthMean": 57.0, "recentLandingRate": 0.99 }, { "update": 352, "trainingStep": 1441792, "elapsedSeconds": 58.57546291599283, "environmentStepsPerSecond": 24614.265568293926, "learningRate": 0.00016289062499999998, "loss": 58.45564270019531, "policyLoss": -0.00020326286903582513, "valueLoss": 116.93285465240479, "entropy": 1.058166690170765, "approximateKl": 0.00015782288755872287, "clipFraction": 0.0, "explainedVariance": 0.1335913245536655, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 20022, "recentEpisodeCount": 100, "recentReturnMean": 122.45196298410592, "recentReturnMedian": 128.72446191939525, "recentLengthMean": 55.08, "recentLandingRate": 0.97 }, { "update": 353, "trainingStep": 1445888, "elapsedSeconds": 58.7362132499984, "environmentStepsPerSecond": 24616.636313374176, "learningRate": 0.00016250000000000002, "loss": 60.290087938308716, "policyLoss": -0.0012883251765742898, "valueLoss": 120.6035943031311, "entropy": 1.0421567186713219, "approximateKl": 0.0002645710337674245, "clipFraction": 0.0, "explainedVariance": 0.1370675259599058, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 20093, "recentEpisodeCount": 100, "recentReturnMean": 122.63131708142522, "recentReturnMedian": 128.91495591995772, "recentLengthMean": 55.41, "recentLandingRate": 0.97 }, { "update": 354, "trainingStep": 1449984, "elapsedSeconds": 58.89312220798456, "environmentStepsPerSecond": 24620.59992131671, "learningRate": 0.00016210937499999995, "loss": 74.24853515625, "policyLoss": -0.000823019741801545, "valueLoss": 148.51976823806763, "entropy": 1.0525887608528137, "approximateKl": 0.0005884848214918748, "clipFraction": 0.0, "explainedVariance": 0.12114877741986163, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 20170, "recentEpisodeCount": 100, "recentReturnMean": 118.03842043077223, "recentReturnMedian": 128.52484612927947, "recentLengthMean": 55.19, "recentLandingRate": 0.95 }, { "update": 355, "trainingStep": 1454080, "elapsedSeconds": 59.0518562909856, "environmentStepsPerSecond": 24623.781390289143, "learningRate": 0.00016171875, "loss": 56.86131191253662, "policyLoss": -0.0006126831285655499, "valueLoss": 113.74472522735596, "entropy": 1.0438266098499298, "approximateKl": 0.0004012860845250543, "clipFraction": 0.0, "explainedVariance": 0.14352190494869965, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 20242, "recentEpisodeCount": 100, "recentReturnMean": 122.55427185815323, "recentReturnMedian": 128.8191837449558, "recentLengthMean": 56.06, "recentLandingRate": 0.97 }, { "update": 356, "trainingStep": 1458176, "elapsedSeconds": 59.20400649998919, "environmentStepsPerSecond": 24629.684479212843, "learningRate": 0.000161328125, "loss": 40.97581434249878, "policyLoss": -9.860887075774372e-05, "valueLoss": 81.97320914268494, "entropy": 1.0691945403814316, "approximateKl": 4.105118568986654e-05, "clipFraction": 0.0, "explainedVariance": 0.2156934794544041, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 20311, "recentEpisodeCount": 100, "recentReturnMean": 124.46833754846266, "recentReturnMedian": 128.56197572650854, "recentLengthMean": 57.68, "recentLandingRate": 0.98 }, { "update": 357, "trainingStep": 1462272, "elapsedSeconds": 59.357236082985764, "environmentStepsPerSecond": 24635.109322739296, "learningRate": 0.00016093749999999997, "loss": 65.95230460166931, "policyLoss": -0.0004688466142397374, "valueLoss": 131.92669773101807, "entropy": 1.0574885457754135, "approximateKl": 5.7984041632153094e-05, "clipFraction": 0.0, "explainedVariance": 0.1308114620651133, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 20387, "recentEpisodeCount": 100, "recentReturnMean": 120.2754684793669, "recentReturnMedian": 128.53220254316693, "recentLengthMean": 57.17, "recentLandingRate": 0.96 }, { "update": 358, "trainingStep": 1466368, "elapsedSeconds": 59.50851762498496, "environmentStepsPerSecond": 24641.31284937835, "learningRate": 0.000160546875, "loss": 40.002097725868225, "policyLoss": -0.0004027094109915197, "valueLoss": 80.02628707885742, "entropy": 1.0642787590622902, "approximateKl": 9.953309927368537e-05, "clipFraction": 0.0, "explainedVariance": 0.20907426104052285, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 20457, "recentEpisodeCount": 100, "recentReturnMean": 126.26341660900238, "recentReturnMedian": 128.63415370730218, "recentLengthMean": 57.23, "recentLandingRate": 0.99 }, { "update": 359, "trainingStep": 1470464, "elapsedSeconds": 59.68680587498238, "environmentStepsPerSecond": 24636.332577085388, "learningRate": 0.00016015625, "loss": 39.37033760547638, "policyLoss": -0.0012525107595138252, "valueLoss": 78.76444482803345, "entropy": 1.0632087960839272, "approximateKl": 0.00044764389531337656, "clipFraction": 0.0, "explainedVariance": 0.19360351176930868, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 20523, "recentEpisodeCount": 100, "recentReturnMean": 124.28035820861754, "recentReturnMedian": 128.54357026191428, "recentLengthMean": 57.88, "recentLandingRate": 0.98 }, { "update": 360, "trainingStep": 1474560, "elapsedSeconds": 59.86335220799083, "environmentStepsPerSecond": 24632.098698327976, "learningRate": 0.00015976562499999997, "loss": 59.31865668296814, "policyLoss": 7.401456241495907e-05, "valueLoss": 118.65833234786987, "entropy": 1.0583296567201614, "approximateKl": 0.0001686170362518169, "clipFraction": 0.0, "explainedVariance": 0.15289174450886844, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 20602, "recentEpisodeCount": 100, "recentReturnMean": 122.72155072688707, "recentReturnMedian": 128.9371792380698, "recentLengthMean": 56.97, "recentLandingRate": 0.97 }, { "update": 361, "trainingStep": 1478656, "elapsedSeconds": 60.02371637499891, "environmentStepsPerSecond": 24634.529304418247, "learningRate": 0.00015937499999999998, "loss": 70.97971296310425, "policyLoss": -0.001043671218212694, "valueLoss": 141.9822554588318, "entropy": 1.037069909274578, "approximateKl": 0.0003150070187984966, "clipFraction": 6.103515625e-05, "explainedVariance": 0.1092779869828685, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 20672, "recentEpisodeCount": 100, "recentReturnMean": 122.94252833742422, "recentReturnMedian": 129.50483461626573, "recentLengthMean": 56.71, "recentLandingRate": 0.97 }, { "update": 362, "trainingStep": 1482752, "elapsedSeconds": 60.181918999995105, "environmentStepsPerSecond": 24637.831837833564, "learningRate": 0.000158984375, "loss": 62.14841413497925, "policyLoss": -0.0006845425232313573, "valueLoss": 124.3191146850586, "entropy": 1.045852854847908, "approximateKl": 0.0006427188309316989, "clipFraction": 0.000244140625, "explainedVariance": 0.11558172664239041, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 20739, "recentEpisodeCount": 100, "recentReturnMean": 118.30047756232503, "recentReturnMedian": 129.14530188869685, "recentLengthMean": 56.6, "recentLandingRate": 0.95 }, { "update": 363, "trainingStep": 1486848, "elapsedSeconds": 60.339885332999984, "environmentStepsPerSecond": 24641.213548790758, "learningRate": 0.00015859374999999996, "loss": 75.28154802322388, "policyLoss": -0.0017294119315920398, "valueLoss": 150.58749103546143, "entropy": 1.046930730342865, "approximateKl": 0.002463847769831773, "clipFraction": 0.02020263671875, "explainedVariance": 0.11147735948649273, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 20817, "recentEpisodeCount": 100, "recentReturnMean": 118.27603998599545, "recentReturnMedian": 128.85801927908324, "recentLengthMean": 56.62, "recentLandingRate": 0.95 }, { "update": 364, "trainingStep": 1490944, "elapsedSeconds": 60.49390424997546, "environmentStepsPerSecond": 24646.18573532729, "learningRate": 0.00015820312499999998, "loss": 39.883959889411926, "policyLoss": -0.0010468009277246892, "valueLoss": 79.79132604598999, "entropy": 1.0656085386872292, "approximateKl": 0.0006633549601247068, "clipFraction": 0.0, "explainedVariance": 0.2249113042434172, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 20886, "recentEpisodeCount": 100, "recentReturnMean": 122.90766355125852, "recentReturnMedian": 129.2686287657125, "recentLengthMean": 57.33, "recentLandingRate": 0.97 }, { "update": 365, "trainingStep": 1495040, "elapsedSeconds": 60.65207974999794, "environmentStepsPerSecond": 24649.44328640356, "learningRate": 0.00015781250000000002, "loss": 71.7238073348999, "policyLoss": -0.00038104603299871087, "valueLoss": 143.46917581558228, "entropy": 1.0398411601781845, "approximateKl": 0.0001465589230065234, "clipFraction": 0.0, "explainedVariance": 0.1138721464903999, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 20958, "recentEpisodeCount": 100, "recentReturnMean": 120.67968091633352, "recentReturnMedian": 129.39446957735345, "recentLengthMean": 56.5, "recentLandingRate": 0.96 }, { "update": 366, "trainingStep": 1499136, "elapsedSeconds": 60.81316049999441, "environmentStepsPerSecond": 24651.506148905675, "learningRate": 0.00015742187499999996, "loss": 86.95958995819092, "policyLoss": -0.0013239241670817137, "valueLoss": 173.94252586364746, "entropy": 1.0349314659833908, "approximateKl": 0.0004570071614580229, "clipFraction": 0.000244140625, "explainedVariance": 0.09573071853012582, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 21034, "recentEpisodeCount": 100, "recentReturnMean": 118.90036866613838, "recentReturnMedian": 129.7225682050921, "recentLengthMean": 55.62, "recentLandingRate": 0.95 }, { "update": 367, "trainingStep": 1503232, "elapsedSeconds": 60.96977349999361, "environmentStepsPerSecond": 24655.364678370628, "learningRate": 0.00015703125, "loss": 54.32565212249756, "policyLoss": -0.0006787078164052218, "valueLoss": 108.67365503311157, "entropy": 1.049747921526432, "approximateKl": 0.0005017748335376382, "clipFraction": 0.00018310546875, "explainedVariance": 0.15478379954139243, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 21107, "recentEpisodeCount": 100, "recentReturnMean": 122.14133309513709, "recentReturnMedian": 128.3106079287827, "recentLengthMean": 57.81, "recentLandingRate": 0.97 }, { "update": 368, "trainingStep": 1507328, "elapsedSeconds": 61.13148391598952, "environmentStepsPerSecond": 24657.147241370072, "learningRate": 0.00015664062500000001, "loss": 56.445639848709106, "policyLoss": -0.0014365926035679877, "valueLoss": 112.91493511199951, "entropy": 1.039134867489338, "approximateKl": 0.0017289644347329158, "clipFraction": 0.00830078125, "explainedVariance": 0.15340866753126547, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 21180, "recentEpisodeCount": 100, "recentReturnMean": 122.58791108964859, "recentReturnMedian": 128.88920143822907, "recentLengthMean": 57.06, "recentLandingRate": 0.97 }, { "update": 369, "trainingStep": 1511424, "elapsedSeconds": 61.2882934579975, "environmentStepsPerSecond": 24660.89223117004, "learningRate": 0.00015624999999999998, "loss": 21.088317036628723, "policyLoss": 4.52663516625762e-06, "valueLoss": 42.19760799407959, "entropy": 1.049168236553669, "approximateKl": 0.0003825775202130899, "clipFraction": 0.0, "explainedVariance": 0.4265972362948671, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 21248, "recentEpisodeCount": 100, "recentReturnMean": 124.59089336298688, "recentReturnMedian": 128.7904190258123, "recentLengthMean": 57.48, "recentLandingRate": 0.98 }, { "update": 370, "trainingStep": 1515520, "elapsedSeconds": 61.44010279097711, "environmentStepsPerSecond": 24666.625398656794, "learningRate": 0.000155859375, "loss": 53.98750376701355, "policyLoss": -0.0006420917343348265, "valueLoss": 107.99727058410645, "entropy": 1.0490339323878288, "approximateKl": 0.000471812512842007, "clipFraction": 0.0003662109375, "explainedVariance": 0.1512934968273446, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 21319, "recentEpisodeCount": 100, "recentReturnMean": 124.59857191998817, "recentReturnMedian": 129.03976032463834, "recentLengthMean": 57.7, "recentLandingRate": 0.98 }, { "update": 371, "trainingStep": 1519616, "elapsedSeconds": 61.593178249982884, "environmentStepsPerSecond": 24671.8231332773, "learningRate": 0.00015546875, "loss": 36.20566248893738, "policyLoss": -0.0005939530674368143, "valueLoss": 72.43342185020447, "entropy": 1.0454391911625862, "approximateKl": 0.0009211454707838129, "clipFraction": 0.0013427734375, "explainedVariance": 0.23789205174662664, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 21390, "recentEpisodeCount": 100, "recentReturnMean": 125.01690822917575, "recentReturnMedian": 129.08323357300833, "recentLengthMean": 56.97, "recentLandingRate": 0.98 }, { "update": 372, "trainingStep": 1523712, "elapsedSeconds": 61.74942529099644, "environmentStepsPerSecond": 24675.72763340632, "learningRate": 0.00015507812499999997, "loss": 26.941432118415833, "policyLoss": -0.0017493608902441338, "valueLoss": 53.90722441673279, "entropy": 1.0430721566081047, "approximateKl": 0.000980347493168665, "clipFraction": 0.00213623046875, "explainedVariance": 0.295691257066537, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 21462, "recentEpisodeCount": 100, "recentReturnMean": 127.32796949239622, "recentReturnMedian": 129.4967633621709, "recentLengthMean": 56.76, "recentLandingRate": 0.99 }, { "update": 373, "trainingStep": 1527808, "elapsedSeconds": 61.908581415977096, "environmentStepsPerSecond": 24678.452729102755, "learningRate": 0.00015468749999999999, "loss": 53.28601777553558, "policyLoss": -0.000630224822089076, "valueLoss": 106.59409308433533, "entropy": 1.0398074388504028, "approximateKl": 0.0004787875586771406, "clipFraction": 0.0, "explainedVariance": 0.12254877958412358, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 21531, "recentEpisodeCount": 100, "recentReturnMean": 124.47206017772896, "recentReturnMedian": 128.89630747470073, "recentLengthMean": 59.14, "recentLandingRate": 0.98 }, { "update": 374, "trainingStep": 1531904, "elapsedSeconds": 62.065293374995235, "environmentStepsPerSecond": 24682.135807275037, "learningRate": 0.000154296875, "loss": 71.53577280044556, "policyLoss": -0.0007061348878778517, "valueLoss": 143.09374284744263, "entropy": 1.0393280684947968, "approximateKl": 0.0004842544440180063, "clipFraction": 0.0, "explainedVariance": 0.11342399883763854, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 21607, "recentEpisodeCount": 100, "recentReturnMean": 122.3802959006769, "recentReturnMedian": 128.78070295788348, "recentLengthMean": 54.49, "recentLandingRate": 0.97 }, { "update": 375, "trainingStep": 1536000, "elapsedSeconds": 62.2243557079928, "environmentStepsPerSecond": 24684.867886911663, "learningRate": 0.00015390624999999996, "loss": 20.266105890274048, "policyLoss": 0.0002117434050887823, "valueLoss": 40.55275845527649, "entropy": 1.0485167801380157, "approximateKl": 0.00032880495928111486, "clipFraction": 0.0, "explainedVariance": 0.42539229403347767, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 21677, "recentEpisodeCount": 100, "recentReturnMean": 122.20823206776346, "recentReturnMedian": 128.5249312054366, "recentLengthMean": 55.49, "recentLandingRate": 0.97 }, { "update": 376, "trainingStep": 1540096, "elapsedSeconds": 62.37824424999417, "environmentStepsPerSecond": 24689.63367785306, "learningRate": 0.00015351562499999998, "loss": 39.33568799495697, "policyLoss": -0.0004659507249016315, "valueLoss": 78.69319558143616, "entropy": 1.0443744137883186, "approximateKl": 0.00018106278366758488, "clipFraction": 0.0, "explainedVariance": 0.24917732456155506, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 21758, "recentEpisodeCount": 100, "recentReturnMean": 126.55950822350952, "recentReturnMedian": 128.72697345534107, "recentLengthMean": 54.54, "recentLandingRate": 0.99 }, { "update": 377, "trainingStep": 1544192, "elapsedSeconds": 62.54156329098623, "environmentStepsPerSecond": 24690.6524036721, "learningRate": 0.00015312500000000002, "loss": 74.43316531181335, "policyLoss": -0.0011346699466230348, "valueLoss": 148.88926935195923, "entropy": 1.0334038138389587, "approximateKl": 0.00036875996374874376, "clipFraction": 6.103515625e-05, "explainedVariance": 0.10225851553152299, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 21832, "recentEpisodeCount": 100, "recentReturnMean": 118.74234190755415, "recentReturnMedian": 129.2605264056474, "recentLengthMean": 53.97, "recentLandingRate": 0.95 }, { "update": 378, "trainingStep": 1548288, "elapsedSeconds": 62.70972045799135, "environmentStepsPerSecond": 24689.760832807147, "learningRate": 0.00015273437499999996, "loss": 52.097694873809814, "policyLoss": -0.0009104232012759894, "valueLoss": 104.21797752380371, "entropy": 1.0382921770215034, "approximateKl": 0.0005937208225077484, "clipFraction": 0.0, "explainedVariance": 0.1539826901665301, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 21903, "recentEpisodeCount": 100, "recentReturnMean": 121.255734821191, "recentReturnMedian": 129.7212979674805, "recentLengthMean": 55.01, "recentLandingRate": 0.96 }, { "update": 379, "trainingStep": 1552384, "elapsedSeconds": 62.86714062499232, "environmentStepsPerSecond": 24693.09061247272, "learningRate": 0.00015234375, "loss": 52.04275727272034, "policyLoss": -0.001332467218162492, "valueLoss": 104.10896348953247, "entropy": 1.0391829460859299, "approximateKl": 0.0006607558352698106, "clipFraction": 6.103515625e-05, "explainedVariance": 0.16650229703602537, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 21982, "recentEpisodeCount": 100, "recentReturnMean": 122.58890783326788, "recentReturnMedian": 129.0272194792051, "recentLengthMean": 55.14, "recentLandingRate": 0.97 }, { "update": 380, "trainingStep": 1556480, "elapsedSeconds": 63.03145179100102, "environmentStepsPerSecond": 24693.70379030708, "learningRate": 0.00015195312500000002, "loss": 34.75408673286438, "policyLoss": -0.0007588732987642288, "valueLoss": 69.53072333335876, "entropy": 1.0516316294670105, "approximateKl": 0.0004089321919309441, "clipFraction": 0.0003662109375, "explainedVariance": 0.2207043144593227, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 22054, "recentEpisodeCount": 100, "recentReturnMean": 126.36902302098301, "recentReturnMedian": 128.18090519124962, "recentLengthMean": 57.35, "recentLandingRate": 0.99 }, { "update": 381, "trainingStep": 1560576, "elapsedSeconds": 63.19534916599514, "environmentStepsPerSecond": 24694.475473200364, "learningRate": 0.00015156249999999998, "loss": 31.576903223991394, "policyLoss": -2.9935181373730302e-05, "valueLoss": 63.174975633621216, "entropy": 1.0555049628019333, "approximateKl": 0.00023374484953819774, "clipFraction": 0.0, "explainedVariance": 0.22344904451569336, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 22119, "recentEpisodeCount": 100, "recentReturnMean": 124.27444824118123, "recentReturnMedian": 128.1941213560276, "recentLengthMean": 58.5, "recentLandingRate": 0.98 }, { "update": 382, "trainingStep": 1564672, "elapsedSeconds": 63.35504741600016, "environmentStepsPerSecond": 24696.87994590382, "learningRate": 0.000151171875, "loss": 32.49293231964111, "policyLoss": -0.0009101844188990071, "valueLoss": 65.00907874107361, "entropy": 1.0696710795164108, "approximateKl": 0.00047735402404214256, "clipFraction": 0.0, "explainedVariance": 0.20543087227408396, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 22186, "recentEpisodeCount": 100, "recentReturnMean": 124.1228565558092, "recentReturnMedian": 128.1041131534148, "recentLengthMean": 58.92, "recentLandingRate": 0.98 }, { "update": 383, "trainingStep": 1568768, "elapsedSeconds": 63.51483887498034, "environmentStepsPerSecond": 24699.23608068801, "learningRate": 0.00015078125, "loss": 34.04157555103302, "policyLoss": -0.0011385865218471736, "valueLoss": 68.10625720024109, "entropy": 1.0413676649332047, "approximateKl": 0.0012111740034015384, "clipFraction": 0.00213623046875, "explainedVariance": 0.2501286073350488, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 22260, "recentEpisodeCount": 100, "recentReturnMean": 126.75259712408632, "recentReturnMedian": 128.5485319950385, "recentLengthMean": 57.78, "recentLandingRate": 0.99 }, { "update": 384, "trainingStep": 1572864, "elapsedSeconds": 63.67194062497583, "environmentStepsPerSecond": 24702.623864789686, "learningRate": 0.00015039062499999997, "loss": 52.7991669178009, "policyLoss": -0.0005391686281654984, "valueLoss": 105.62024450302124, "entropy": 1.0416131019592285, "approximateKl": 0.00020788077017641626, "clipFraction": 0.0, "explainedVariance": 0.1570627468987188, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 22336, "recentEpisodeCount": 100, "recentReturnMean": 122.13707303282281, "recentReturnMedian": 128.13501555821858, "recentLengthMean": 56.6, "recentLandingRate": 0.97 }, { "update": 385, "trainingStep": 1576960, "elapsedSeconds": 63.84029333299259, "environmentStepsPerSecond": 24701.640886493686, "learningRate": 0.00015, "loss": 56.95358729362488, "policyLoss": -7.031706627458334e-05, "valueLoss": 113.92832612991333, "entropy": 1.0505362376570702, "approximateKl": 7.556662239949219e-05, "clipFraction": 0.0, "explainedVariance": 0.13248124175442977, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 22407, "recentEpisodeCount": 100, "recentReturnMean": 123.04157582825631, "recentReturnMedian": 129.40509381261654, "recentLengthMean": 56.32, "recentLandingRate": 0.97 }, { "update": 386, "trainingStep": 1581056, "elapsedSeconds": 64.00450874998933, "environmentStepsPerSecond": 24702.259745103718, "learningRate": 0.00014960937499999998, "loss": 36.20412576198578, "policyLoss": -0.00045729277189821005, "valueLoss": 72.42999386787415, "entropy": 1.041394017636776, "approximateKl": 0.00029439798163366504, "clipFraction": 0.0, "explainedVariance": 0.23967705261214844, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 22482, "recentEpisodeCount": 100, "recentReturnMean": 124.87794775122995, "recentReturnMedian": 129.14687849141774, "recentLengthMean": 55.03, "recentLandingRate": 0.98 }, { "update": 387, "trainingStep": 1585152, "elapsedSeconds": 64.17727662497782, "environmentStepsPerSecond": 24699.583456351564, "learningRate": 0.00014921875, "loss": 32.57145702838898, "policyLoss": -0.0006021333392709494, "valueLoss": 65.16464447975159, "entropy": 1.0263002589344978, "approximateKl": 0.0001399821339873597, "clipFraction": 0.0, "explainedVariance": 0.25199877121014136, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 22555, "recentEpisodeCount": 100, "recentReturnMean": 126.55042748973305, "recentReturnMedian": 128.5541692432016, "recentLengthMean": 55.52, "recentLandingRate": 0.99 }, { "update": 388, "trainingStep": 1589248, "elapsedSeconds": 64.33514908299549, "environmentStepsPerSecond": 24702.63957809117, "learningRate": 0.00014882812499999998, "loss": 18.157578945159912, "policyLoss": -0.0002110025379806757, "valueLoss": 36.33623933792114, "entropy": 1.0329740047454834, "approximateKl": 0.0005195376688789111, "clipFraction": 0.0, "explainedVariance": 0.4873258228242746, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 22630, "recentEpisodeCount": 100, "recentReturnMean": 128.98595114649274, "recentReturnMedian": 129.059451112058, "recentLengthMean": 54.69, "recentLandingRate": 1.0 }, { "update": 389, "trainingStep": 1593344, "elapsedSeconds": 64.49292637498002, "environmentStepsPerSecond": 24705.717193477154, "learningRate": 0.00014843749999999997, "loss": 52.72685217857361, "policyLoss": -0.0004096365300938487, "valueLoss": 105.47526216506958, "entropy": 1.0369398817420006, "approximateKl": 0.0005150484357727692, "clipFraction": 6.103515625e-05, "explainedVariance": 0.1536241560812983, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 22706, "recentEpisodeCount": 100, "recentReturnMean": 124.7223756433776, "recentReturnMedian": 128.99726000986993, "recentLengthMean": 54.6, "recentLandingRate": 0.98 }, { "update": 390, "trainingStep": 1597440, "elapsedSeconds": 64.65996224997798, "environmentStepsPerSecond": 24705.24176652367, "learningRate": 0.00014804687499999999, "loss": 86.57186698913574, "policyLoss": -0.0007559431542176753, "valueLoss": 173.16610383987427, "entropy": 1.042906939983368, "approximateKl": 0.0005843665894644801, "clipFraction": 0.00042724609375, "explainedVariance": 0.07748058482111597, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 22779, "recentEpisodeCount": 100, "recentReturnMean": 117.87176641899637, "recentReturnMedian": 128.34353553690016, "recentLengthMean": 54.91, "recentLandingRate": 0.95 }, { "update": 391, "trainingStep": 1601536, "elapsedSeconds": 64.82236958298017, "environmentStepsPerSecond": 24706.532795748044, "learningRate": 0.00014765624999999997, "loss": 48.9514844417572, "policyLoss": -0.0011215921840630472, "valueLoss": 97.92580938339233, "entropy": 1.0298671200871468, "approximateKl": 0.0023518154448538553, "clipFraction": 0.0203857421875, "explainedVariance": 0.15934065288385046, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 22850, "recentEpisodeCount": 100, "recentReturnMean": 120.60356323055923, "recentReturnMedian": 129.11557261087, "recentLengthMean": 54.96, "recentLandingRate": 0.96 }, { "update": 392, "trainingStep": 1605632, "elapsedSeconds": 64.97949924998102, "environmentStepsPerSecond": 24709.824152737972, "learningRate": 0.00014726562499999996, "loss": 84.97491073608398, "policyLoss": -0.0007957200868986547, "valueLoss": 169.97200727462769, "entropy": 1.02971513569355, "approximateKl": 0.0009673925669630989, "clipFraction": 0.0029296875, "explainedVariance": 0.10408559444424237, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 22932, "recentEpisodeCount": 100, "recentReturnMean": 120.36552234673502, "recentReturnMedian": 128.77043688390404, "recentLengthMean": 54.5, "recentLandingRate": 0.96 }, { "update": 393, "trainingStep": 1609728, "elapsedSeconds": 65.14912504097447, "environmentStepsPerSecond": 24708.359459740834, "learningRate": 0.000146875, "loss": 68.87077283859253, "policyLoss": -0.0007870772969909012, "valueLoss": 137.76342678070068, "entropy": 1.0154245644807816, "approximateKl": 0.0006370422997861169, "clipFraction": 6.103515625e-05, "explainedVariance": 0.12267533065168068, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 23004, "recentEpisodeCount": 100, "recentReturnMean": 116.50621214676285, "recentReturnMedian": 129.41636088490486, "recentLengthMean": 54.21, "recentLandingRate": 0.94 }, { "update": 394, "trainingStep": 1613824, "elapsedSeconds": 65.31756754100206, "environmentStepsPerSecond": 24707.34996349868, "learningRate": 0.000146484375, "loss": 68.1091799736023, "policyLoss": -0.0004803310876013711, "valueLoss": 136.23967695236206, "entropy": 1.01789890229702, "approximateKl": 0.00017465425116824917, "clipFraction": 0.0, "explainedVariance": 0.11969733194686183, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 23080, "recentEpisodeCount": 100, "recentReturnMean": 120.20845318675565, "recentReturnMedian": 128.04168894223403, "recentLengthMean": 54.94, "recentLandingRate": 0.96 }, { "update": 395, "trainingStep": 1617920, "elapsedSeconds": 65.48060258297483, "environmentStepsPerSecond": 24708.385936886058, "learningRate": 0.00014609374999999998, "loss": 103.82939577102661, "policyLoss": -0.0019437405571807176, "valueLoss": 207.6832504272461, "entropy": 1.028443455696106, "approximateKl": 0.006098504003603011, "clipFraction": 0.08624267578125, "explainedVariance": 0.06257934399024168, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 23154, "recentEpisodeCount": 100, "recentReturnMean": 115.88067406722534, "recentReturnMedian": 128.46752962470055, "recentLengthMean": 54.37, "recentLandingRate": 0.94 }, { "update": 396, "trainingStep": 1622016, "elapsedSeconds": 65.6364186249848, "environmentStepsPerSecond": 24712.134421401417, "learningRate": 0.000145703125, "loss": 50.593642234802246, "policyLoss": 0.00010965135879814625, "valueLoss": 101.20758509635925, "entropy": 1.0259846821427345, "approximateKl": 0.00021766352438135073, "clipFraction": 0.0, "explainedVariance": 0.17133546758242302, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 23228, "recentEpisodeCount": 100, "recentReturnMean": 124.54455436899757, "recentReturnMedian": 129.0142291211523, "recentLengthMean": 54.57, "recentLandingRate": 0.98 }, { "update": 397, "trainingStep": 1626112, "elapsedSeconds": 65.79497866597376, "environmentStepsPerSecond": 24714.834368370317, "learningRate": 0.0001453125, "loss": 52.45529580116272, "policyLoss": -5.620156298391521e-05, "valueLoss": 104.93138027191162, "entropy": 1.0339083448052406, "approximateKl": 3.150950578856282e-05, "clipFraction": 0.0, "explainedVariance": 0.17311252975246227, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 23306, "recentEpisodeCount": 100, "recentReturnMean": 122.60106812724072, "recentReturnMedian": 128.74430035427213, "recentLengthMean": 54.99, "recentLandingRate": 0.97 }, { "update": 398, "trainingStep": 1630208, "elapsedSeconds": 65.95930370799033, "environmentStepsPerSecond": 24715.36096283133, "learningRate": 0.00014492187499999998, "loss": 30.7353515625, "policyLoss": -0.0005189430376049131, "valueLoss": 61.492469787597656, "entropy": 1.036468617618084, "approximateKl": 0.0002758480331976898, "clipFraction": 0.0, "explainedVariance": 0.27566920884324275, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 23377, "recentEpisodeCount": 100, "recentReturnMean": 122.92597497964366, "recentReturnMedian": 129.38340939907357, "recentLengthMean": 55.26, "recentLandingRate": 0.97 }, { "update": 399, "trainingStep": 1634304, "elapsedSeconds": 66.13422429098864, "environmentStepsPerSecond": 24711.92514195238, "learningRate": 0.00014453125, "loss": 51.040974140167236, "policyLoss": -0.00027937906270381063, "valueLoss": 102.10300397872925, "entropy": 1.0248170718550682, "approximateKl": 4.4859174522571266e-05, "clipFraction": 0.0, "explainedVariance": 0.166089116200536, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 23451, "recentEpisodeCount": 100, "recentReturnMean": 125.07004746485211, "recentReturnMedian": 129.35056501982035, "recentLengthMean": 54.72, "recentLandingRate": 0.98 }, { "update": 400, "trainingStep": 1638400, "elapsedSeconds": 66.2986963329895, "environmentStepsPerSecond": 24712.40145916339, "learningRate": 0.00014414062499999998, "loss": 30.78753674030304, "policyLoss": -0.0014308548416011035, "valueLoss": 61.59855270385742, "entropy": 1.0308797284960747, "approximateKl": 0.0005425875024229754, "clipFraction": 0.0001220703125, "explainedVariance": 0.2824011805851647, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 23527, "recentEpisodeCount": 100, "recentReturnMean": 127.3024245358065, "recentReturnMedian": 129.32368943467736, "recentLengthMean": 54.48, "recentLandingRate": 0.99 }, { "update": 401, "trainingStep": 1642496, "elapsedSeconds": 66.47687074998976, "environmentStepsPerSecond": 24707.781540698546, "learningRate": 0.00014374999999999997, "loss": 32.075942397117615, "policyLoss": -0.00040131641435436904, "valueLoss": 64.17304062843323, "entropy": 1.0176276117563248, "approximateKl": 0.0004862901914748363, "clipFraction": 0.0, "explainedVariance": 0.2639602573430805, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 23603, "recentEpisodeCount": 100, "recentReturnMean": 126.52493935230886, "recentReturnMedian": 128.54576669792004, "recentLengthMean": 53.87, "recentLandingRate": 0.99 }, { "update": 402, "trainingStep": 1646592, "elapsedSeconds": 66.65259983297437, "environmentStepsPerSecond": 24704.092625437213, "learningRate": 0.00014335937499999999, "loss": 83.0894672870636, "policyLoss": -0.003404823160963133, "valueLoss": 166.20587873458862, "entropy": 1.0067846961319447, "approximateKl": 0.003367061242897762, "clipFraction": 0.04302978515625, "explainedVariance": 0.07899496622464142, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 23675, "recentEpisodeCount": 100, "recentReturnMean": 120.50739639571678, "recentReturnMedian": 128.9623507174765, "recentLengthMean": 55.07, "recentLandingRate": 0.96 }, { "update": 403, "trainingStep": 1650688, "elapsedSeconds": 66.81993108298047, "environmentStepsPerSecond": 24703.527424326276, "learningRate": 0.00014296874999999998, "loss": 49.497631549835205, "policyLoss": -0.00034256564686074853, "valueLoss": 99.01643562316895, "entropy": 1.024244949221611, "approximateKl": 0.0002172554777644109, "clipFraction": 0.0, "explainedVariance": 0.16126750002064427, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 23748, "recentEpisodeCount": 100, "recentReturnMean": 122.98102993530192, "recentReturnMedian": 129.1870581479743, "recentLengthMean": 56.93, "recentLandingRate": 0.97 }, { "update": 404, "trainingStep": 1654784, "elapsedSeconds": 66.97683766597765, "environmentStepsPerSecond": 24706.80996096929, "learningRate": 0.00014257812499999996, "loss": 13.099674820899963, "policyLoss": -0.0013072238652966917, "valueLoss": 26.222676038742065, "entropy": 1.0355848371982574, "approximateKl": 0.0011413092397560831, "clipFraction": 0.0020751953125, "explainedVariance": 0.5944915651711691, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 23824, "recentEpisodeCount": 100, "recentReturnMean": 127.14009645320671, "recentReturnMedian": 129.28083243733272, "recentLengthMean": 55.86, "recentLandingRate": 0.99 }, { "update": 405, "trainingStep": 1658880, "elapsedSeconds": 67.13113083297503, "environmentStepsPerSecond": 24711.03911726678, "learningRate": 0.0001421875, "loss": 31.629151105880737, "policyLoss": -0.00017302800551988184, "valueLoss": 63.279417991638184, "entropy": 1.0384466722607613, "approximateKl": 0.00017237665451830253, "clipFraction": 0.0, "explainedVariance": 0.25336631943113674, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 23894, "recentEpisodeCount": 100, "recentReturnMean": 126.71209720922394, "recentReturnMedian": 128.6861273299437, "recentLengthMean": 54.27, "recentLandingRate": 0.99 }, { "update": 406, "trainingStep": 1662976, "elapsedSeconds": 67.29291254098644, "environmentStepsPerSecond": 24712.498496585697, "learningRate": 0.000141796875, "loss": 49.4967200756073, "policyLoss": -0.0008561090799048543, "valueLoss": 99.01549863815308, "entropy": 1.0172863230109215, "approximateKl": 0.0009957919719454367, "clipFraction": 0.00311279296875, "explainedVariance": 0.1689975874101074, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 23972, "recentEpisodeCount": 100, "recentReturnMean": 122.47245477295354, "recentReturnMedian": 128.78047865023836, "recentLengthMean": 55.25, "recentLandingRate": 0.97 }, { "update": 407, "trainingStep": 1667072, "elapsedSeconds": 67.46640658300021, "environmentStepsPerSecond": 24709.66047301027, "learningRate": 0.00014140624999999998, "loss": 13.212896466255188, "policyLoss": 8.286788943223655e-05, "valueLoss": 26.446165442466736, "entropy": 1.0269178748130798, "approximateKl": 0.00023019285799819045, "clipFraction": 0.0, "explainedVariance": 0.5830963791475112, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 24048, "recentEpisodeCount": 100, "recentReturnMean": 128.95996115476493, "recentReturnMedian": 128.7490748334676, "recentLengthMean": 53.91, "recentLandingRate": 1.0 }, { "update": 408, "trainingStep": 1671168, "elapsedSeconds": 67.62208349999855, "environmentStepsPerSecond": 24713.3467870749, "learningRate": 0.000141015625, "loss": 30.722521781921387, "policyLoss": -0.00021554600971285254, "valueLoss": 61.46571588516235, "entropy": 1.012047577649355, "approximateKl": 1.9519829947967082e-05, "clipFraction": 0.0, "explainedVariance": 0.27170910170972395, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 24124, "recentEpisodeCount": 100, "recentReturnMean": 126.95369381099881, "recentReturnMedian": 129.08711329568177, "recentLengthMean": 54.22, "recentLandingRate": 0.99 }, { "update": 409, "trainingStep": 1675264, "elapsedSeconds": 67.77659787499579, "environmentStepsPerSecond": 24717.44012719234, "learningRate": 0.000140625, "loss": 63.84065651893616, "policyLoss": -0.0014291252591647208, "valueLoss": 127.70438814163208, "entropy": 1.0108437538146973, "approximateKl": 0.001250617908226559, "clipFraction": 0.00482177734375, "explainedVariance": 0.11859022887658333, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 24198, "recentEpisodeCount": 100, "recentReturnMean": 122.43294773091235, "recentReturnMedian": 128.92439539008774, "recentLengthMean": 54.19, "recentLandingRate": 0.97 }, { "update": 410, "trainingStep": 1679360, "elapsedSeconds": 67.9329400829738, "environmentStepsPerSecond": 24720.849678356586, "learningRate": 0.00014023437499999998, "loss": 31.76332914829254, "policyLoss": -0.00040132872527465224, "valueLoss": 63.547534227371216, "entropy": 1.0036406517028809, "approximateKl": 0.00043183362504350953, "clipFraction": 0.0, "explainedVariance": 0.28571971551343067, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 24278, "recentEpisodeCount": 100, "recentReturnMean": 127.04194835632391, "recentReturnMedian": 129.2023114450276, "recentLengthMean": 53.98, "recentLandingRate": 0.99 }, { "update": 411, "trainingStep": 1683456, "elapsedSeconds": 68.09515679097967, "environmentStepsPerSecond": 24722.110636552665, "learningRate": 0.00013984375, "loss": 10.768795490264893, "policyLoss": -9.799384861253202e-05, "valueLoss": 21.558146834373474, "entropy": 1.017982117831707, "approximateKl": 1.8874990928452462e-05, "clipFraction": 0.0, "explainedVariance": 0.5839090003978007, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 24346, "recentEpisodeCount": 100, "recentReturnMean": 126.92051813144805, "recentReturnMedian": 129.20506005863717, "recentLengthMean": 54.52, "recentLandingRate": 0.99 }, { "update": 412, "trainingStep": 1687552, "elapsedSeconds": 68.28409404098056, "environmentStepsPerSecond": 24713.690994966106, "learningRate": 0.00013945312499999998, "loss": 52.50141620635986, "policyLoss": -0.0006722133257426322, "valueLoss": 105.02414178848267, "entropy": 0.998271819204092, "approximateKl": 0.00024291561203426681, "clipFraction": 0.0, "explainedVariance": 0.1553285979960798, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 24425, "recentEpisodeCount": 100, "recentReturnMean": 122.70196753917357, "recentReturnMedian": 129.40774886854342, "recentLengthMean": 54.46, "recentLandingRate": 0.97 }, { "update": 413, "trainingStep": 1691648, "elapsedSeconds": 68.4664343749755, "environmentStepsPerSecond": 24707.698238456793, "learningRate": 0.00013906249999999997, "loss": 29.317769944667816, "policyLoss": -0.0020095802028663456, "valueLoss": 58.659788370132446, "entropy": 1.0114344656467438, "approximateKl": 0.0014205548504833132, "clipFraction": 0.0072021484375, "explainedVariance": 0.2694452733626155, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 24501, "recentEpisodeCount": 100, "recentReturnMean": 124.70593004655977, "recentReturnMedian": 129.26318276906386, "recentLengthMean": 54.41, "recentLandingRate": 0.98 }, { "update": 414, "trainingStep": 1695744, "elapsedSeconds": 68.63835737499176, "environmentStepsPerSecond": 24705.486332309007, "learningRate": 0.000138671875, "loss": 12.237708508968353, "policyLoss": -0.0012136675359215587, "valueLoss": 24.498284459114075, "entropy": 1.0219945460557938, "approximateKl": 0.0011507984563650098, "clipFraction": 0.00201416015625, "explainedVariance": 0.5346721358052493, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 24572, "recentEpisodeCount": 100, "recentReturnMean": 129.59517573255638, "recentReturnMedian": 129.7575979377143, "recentLengthMean": 54.85, "recentLandingRate": 1.0 }, { "update": 415, "trainingStep": 1699840, "elapsedSeconds": 68.80289500000072, "environmentStepsPerSecond": 24705.93715569646, "learningRate": 0.00013828124999999998, "loss": 66.0137631893158, "policyLoss": -0.0007397419249173254, "valueLoss": 132.04913330078125, "entropy": 1.0063275061547756, "approximateKl": 0.00039591375025338493, "clipFraction": 0.00030517578125, "explainedVariance": 0.11177223284579307, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 24648, "recentEpisodeCount": 100, "recentReturnMean": 122.98121737915004, "recentReturnMedian": 129.36393991671503, "recentLengthMean": 55.15, "recentLandingRate": 0.97 }, { "update": 416, "trainingStep": 1703936, "elapsedSeconds": 68.96304887498263, "environmentStepsPerSecond": 24707.95633019247, "learningRate": 0.00013789062499999997, "loss": 11.369649410247803, "policyLoss": 0.0001355473359581083, "valueLoss": 22.75910711288452, "entropy": 1.0039645917713642, "approximateKl": 0.00011662975157378241, "clipFraction": 0.0, "explainedVariance": 0.6212972116405706, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 24726, "recentEpisodeCount": 100, "recentReturnMean": 127.3418746962017, "recentReturnMedian": 129.90915888454765, "recentLengthMean": 54.11, "recentLandingRate": 0.99 }, { "update": 417, "trainingStep": 1708032, "elapsedSeconds": 69.11860899999738, "environmentStepsPerSecond": 24711.60841793076, "learningRate": 0.0001375, "loss": 50.924468755722046, "policyLoss": -0.0004509194986894727, "valueLoss": 101.86993455886841, "entropy": 1.0047371424734592, "approximateKl": 6.135593866929412e-05, "clipFraction": 0.0, "explainedVariance": 0.16905949484840044, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 24800, "recentEpisodeCount": 100, "recentReturnMean": 122.65761886624861, "recentReturnMedian": 129.3079007245833, "recentLengthMean": 53.53, "recentLandingRate": 0.97 }, { "update": 418, "trainingStep": 1712128, "elapsedSeconds": 69.27330266599893, "environmentStepsPerSecond": 24715.55323780391, "learningRate": 0.000137109375, "loss": 11.912714123725891, "policyLoss": -0.00025382867897860706, "valueLoss": 23.84607207775116, "entropy": 1.0068051628768444, "approximateKl": 0.00015971612083376385, "clipFraction": 0.0, "explainedVariance": 0.6030163468196608, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 24878, "recentEpisodeCount": 100, "recentReturnMean": 129.43411817005676, "recentReturnMedian": 129.5820892159827, "recentLengthMean": 53.62, "recentLandingRate": 1.0 }, { "update": 419, "trainingStep": 1716224, "elapsedSeconds": 69.43551462498726, "environmentStepsPerSecond": 24716.803918990394, "learningRate": 0.00013671874999999999, "loss": 28.613049507141113, "policyLoss": -0.0005573358212132007, "valueLoss": 57.2473886013031, "entropy": 1.0087739750742912, "approximateKl": 0.00035123297493555583, "clipFraction": 0.0, "explainedVariance": 0.2767528107959468, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 24953, "recentEpisodeCount": 100, "recentReturnMean": 127.09571535998104, "recentReturnMedian": 129.28336117143044, "recentLengthMean": 54.29, "recentLandingRate": 0.99 }, { "update": 420, "trainingStep": 1720320, "elapsedSeconds": 69.58780812498298, "environmentStepsPerSecond": 24721.57187233465, "learningRate": 0.000136328125, "loss": 9.188820123672485, "policyLoss": -0.0007185338763520122, "valueLoss": 18.3994197845459, "entropy": 1.017133079469204, "approximateKl": 0.00024686667529749684, "clipFraction": 0.0, "explainedVariance": 0.6174741292676929, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 25026, "recentEpisodeCount": 100, "recentReturnMean": 129.03775937037935, "recentReturnMedian": 129.25993961188942, "recentLengthMean": 55.23, "recentLandingRate": 1.0 }, { "update": 421, "trainingStep": 1724416, "elapsedSeconds": 69.75558050000109, "environmentStepsPerSecond": 24720.832192056278, "learningRate": 0.0001359375, "loss": 82.23892211914062, "policyLoss": -0.0018329882295802236, "valueLoss": 164.50137901306152, "entropy": 0.9934966564178467, "approximateKl": 0.0022354392822308, "clipFraction": 0.0263671875, "explainedVariance": 0.09062921351733122, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 25103, "recentEpisodeCount": 100, "recentReturnMean": 120.42665414980354, "recentReturnMedian": 128.97393964254297, "recentLengthMean": 54.46, "recentLandingRate": 0.96 }, { "update": 422, "trainingStep": 1728512, "elapsedSeconds": 69.91183645799174, "environmentStepsPerSecond": 24724.16814624258, "learningRate": 0.00013554687499999998, "loss": 8.82430213689804, "policyLoss": -0.0006570935947820544, "valueLoss": 17.669918417930603, "entropy": 1.0000057257711887, "approximateKl": 0.000978302919975249, "clipFraction": 0.00274658203125, "explainedVariance": 0.6685994666007076, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 25180, "recentEpisodeCount": 100, "recentReturnMean": 127.32097758996154, "recentReturnMedian": 129.47193187568337, "recentLengthMean": 54.62, "recentLandingRate": 0.99 }, { "update": 423, "trainingStep": 1732608, "elapsedSeconds": 70.06594074997702, "environmentStepsPerSecond": 24728.24858204117, "learningRate": 0.00013515625, "loss": 28.209903359413147, "policyLoss": -0.0001220850390382111, "valueLoss": 56.440049171447754, "entropy": 0.9999152086675167, "approximateKl": 6.180173659231514e-05, "clipFraction": 0.0, "explainedVariance": 0.2893155730414674, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 25257, "recentEpisodeCount": 100, "recentReturnMean": 127.25840961096678, "recentReturnMedian": 129.10225540504325, "recentLengthMean": 55.0, "recentLandingRate": 0.99 }, { "update": 424, "trainingStep": 1736704, "elapsedSeconds": 70.21772879100172, "environmentStepsPerSecond": 24733.126945321474, "learningRate": 0.00013476562499999998, "loss": 9.764066338539124, "policyLoss": -0.0008483970013912767, "valueLoss": 19.54995846748352, "entropy": 1.0064419768750668, "approximateKl": 0.00028662345721386373, "clipFraction": 0.0, "explainedVariance": 0.6137094101363718, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 25328, "recentEpisodeCount": 100, "recentReturnMean": 128.77949681409757, "recentReturnMedian": 128.6194371401798, "recentLengthMean": 54.12, "recentLandingRate": 1.0 }, { "update": 425, "trainingStep": 1740800, "elapsedSeconds": 70.37454916597926, "environmentStepsPerSecond": 24736.21530269844, "learningRate": 0.00013437499999999997, "loss": 65.04244446754456, "policyLoss": -0.00047113950131461024, "valueLoss": 130.10578536987305, "entropy": 0.9977018125355244, "approximateKl": 0.00016675230654072948, "clipFraction": 0.0, "explainedVariance": 0.11185236817458866, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 25405, "recentEpisodeCount": 100, "recentReturnMean": 122.76276114078922, "recentReturnMedian": 129.2539313598536, "recentLengthMean": 53.98, "recentLandingRate": 0.97 }, { "update": 426, "trainingStep": 1744896, "elapsedSeconds": 70.53173995797988, "environmentStepsPerSecond": 24739.160001434, "learningRate": 0.000133984375, "loss": 49.400816202163696, "policyLoss": -0.0015038025449030101, "valueLoss": 98.82449340820312, "entropy": 0.9927256628870964, "approximateKl": 0.0010186596446146723, "clipFraction": 0.00115966796875, "explainedVariance": 0.149645701457234, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 25479, "recentEpisodeCount": 100, "recentReturnMean": 122.79151204985129, "recentReturnMedian": 129.40284174261615, "recentLengthMean": 55.73, "recentLandingRate": 0.97 }, { "update": 427, "trainingStep": 1748992, "elapsedSeconds": 70.68468170799315, "environmentStepsPerSecond": 24743.57891608389, "learningRate": 0.00013359374999999998, "loss": 59.90275478363037, "policyLoss": -0.000792222999734804, "valueLoss": 119.82693862915039, "entropy": 0.992266122251749, "approximateKl": 0.0006087152250984218, "clipFraction": 0.000244140625, "explainedVariance": 0.12236806844505832, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 25550, "recentEpisodeCount": 100, "recentReturnMean": 120.97098907256539, "recentReturnMedian": 130.08899665251374, "recentLengthMean": 56.16, "recentLandingRate": 0.96 }, { "update": 428, "trainingStep": 1753088, "elapsedSeconds": 70.84131645798334, "environmentStepsPerSecond": 24746.688622588954, "learningRate": 0.00013320312499999997, "loss": 7.521447509527206, "policyLoss": -0.001122618850786239, "valueLoss": 15.06514585018158, "entropy": 1.000281423330307, "approximateKl": 0.0009619407501304522, "clipFraction": 0.003662109375, "explainedVariance": 0.6082121643334581, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 25624, "recentEpisodeCount": 100, "recentReturnMean": 128.91323146588485, "recentReturnMedian": 128.93805694766343, "recentLengthMean": 57.32, "recentLandingRate": 1.0 }, { "update": 429, "trainingStep": 1757184, "elapsedSeconds": 70.9910123749869, "environmentStepsPerSecond": 24752.20371162265, "learningRate": 0.0001328125, "loss": 8.208335876464844, "policyLoss": -0.001565693790325895, "valueLoss": 16.439992487430573, "entropy": 1.0094575136899948, "approximateKl": 0.001427326766133774, "clipFraction": 0.00518798828125, "explainedVariance": 0.6552209605326993, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 25700, "recentEpisodeCount": 100, "recentReturnMean": 128.49676620983925, "recentReturnMedian": 128.4047931553796, "recentLengthMean": 55.84, "recentLandingRate": 1.0 }, { "update": 430, "trainingStep": 1761280, "elapsedSeconds": 71.14152574999025, "environmentStepsPerSecond": 24757.411110208603, "learningRate": 0.000132421875, "loss": 7.889409780502319, "policyLoss": -0.0014135452511254698, "valueLoss": 15.8022021651268, "entropy": 1.027781032025814, "approximateKl": 0.0006896281556691974, "clipFraction": 0.0, "explainedVariance": 0.6438027652574196, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 25772, "recentEpisodeCount": 100, "recentReturnMean": 128.5895961038579, "recentReturnMedian": 128.37175119668245, "recentLengthMean": 54.97, "recentLandingRate": 1.0 }, { "update": 431, "trainingStep": 1765376, "elapsedSeconds": 71.29290341597516, "environmentStepsPerSecond": 24762.296321409438, "learningRate": 0.00013203125, "loss": 27.400398790836334, "policyLoss": -0.00041999699897132814, "valueLoss": 54.821516275405884, "entropy": 0.9939509741961956, "approximateKl": 0.00021649875270668417, "clipFraction": 0.0, "explainedVariance": 0.28064699006540716, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 25848, "recentEpisodeCount": 100, "recentReturnMean": 127.03033126741589, "recentReturnMedian": 129.3889610929764, "recentLengthMean": 53.83, "recentLandingRate": 0.99 }, { "update": 432, "trainingStep": 1769472, "elapsedSeconds": 71.44448091599043, "environmentStepsPerSecond": 24767.091555758838, "learningRate": 0.000131640625, "loss": 39.719844937324524, "policyLoss": -0.0005171424127183855, "valueLoss": 79.46061563491821, "entropy": 0.9945019148290157, "approximateKl": 0.00018939732763101347, "clipFraction": 0.0, "explainedVariance": 0.21254680009250637, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 25926, "recentEpisodeCount": 100, "recentReturnMean": 122.74121138812086, "recentReturnMedian": 129.18197337072343, "recentLengthMean": 53.69, "recentLandingRate": 0.97 }, { "update": 433, "trainingStep": 1773568, "elapsedSeconds": 71.60111795799457, "environmentStepsPerSecond": 24770.116034228395, "learningRate": 0.00013125, "loss": 38.32832646369934, "policyLoss": -6.171083077788353e-05, "valueLoss": 76.6769368648529, "entropy": 1.008026346564293, "approximateKl": 0.00019131378576275893, "clipFraction": 0.0, "explainedVariance": 0.18506068936026865, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 26002, "recentEpisodeCount": 100, "recentReturnMean": 122.64137399745348, "recentReturnMedian": 129.0557099590078, "recentLengthMean": 53.56, "recentLandingRate": 0.97 }, { "update": 434, "trainingStep": 1777664, "elapsedSeconds": 71.75486070799525, "environmentStepsPerSecond": 24774.126553379607, "learningRate": 0.00013085937499999998, "loss": 26.561614394187927, "policyLoss": -0.0009409250269527547, "valueLoss": 53.145034432411194, "entropy": 0.9961683861911297, "approximateKl": 0.0005316034039424267, "clipFraction": 0.0, "explainedVariance": 0.2832005466185533, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 26078, "recentEpisodeCount": 100, "recentReturnMean": 127.04166037072136, "recentReturnMedian": 129.4153749308316, "recentLengthMean": 54.3, "recentLandingRate": 0.99 }, { "update": 435, "trainingStep": 1781760, "elapsedSeconds": 71.9074991660018, "environmentStepsPerSecond": 24778.50044383722, "learningRate": 0.00013046875, "loss": 26.231258273124695, "policyLoss": -0.0011024789564544335, "valueLoss": 52.4845495223999, "entropy": 0.9914327077567577, "approximateKl": 0.0007926285943540279, "clipFraction": 0.00091552734375, "explainedVariance": 0.2788952076203749, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 26150, "recentEpisodeCount": 100, "recentReturnMean": 126.86675669727484, "recentReturnMedian": 129.02809714572504, "recentLengthMean": 54.01, "recentLandingRate": 0.99 }, { "update": 436, "trainingStep": 1785856, "elapsedSeconds": 72.05835424998077, "environmentStepsPerSecond": 24783.46915618707, "learningRate": 0.00013007812499999999, "loss": 7.262856751680374, "policyLoss": -0.0007881757337599993, "valueLoss": 14.547244668006897, "entropy": 0.997735433280468, "approximateKl": 0.00014685302812722512, "clipFraction": 0.0, "explainedVariance": 0.6610532918661955, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 26227, "recentEpisodeCount": 100, "recentReturnMean": 129.35259093295318, "recentReturnMedian": 129.41330708703026, "recentLengthMean": 55.81, "recentLandingRate": 1.0 }, { "update": 437, "trainingStep": 1789952, "elapsedSeconds": 72.21890354098286, "environmentStepsPerSecond": 24785.089668167504, "learningRate": 0.00012968749999999997, "loss": 7.661451280117035, "policyLoss": -0.0008820114308036864, "valueLoss": 15.344656348228455, "entropy": 0.9994889721274376, "approximateKl": 0.00040026817805483006, "clipFraction": 6.103515625e-05, "explainedVariance": 0.641068377737553, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 26299, "recentEpisodeCount": 100, "recentReturnMean": 129.28040698143568, "recentReturnMedian": 129.07476273318753, "recentLengthMean": 54.3, "recentLandingRate": 1.0 }, { "update": 438, "trainingStep": 1794048, "elapsedSeconds": 72.37959374999627, "environmentStepsPerSecond": 24786.654733055784, "learningRate": 0.000129296875, "loss": 26.979659140110016, "policyLoss": -0.0008339504129253328, "valueLoss": 53.980849266052246, "entropy": 0.9931249693036079, "approximateKl": 0.0005612647510133684, "clipFraction": 6.103515625e-05, "explainedVariance": 0.2654484993534949, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 26373, "recentEpisodeCount": 100, "recentReturnMean": 126.6690960656411, "recentReturnMedian": 128.90209068357944, "recentLengthMean": 54.88, "recentLandingRate": 0.99 }, { "update": 439, "trainingStep": 1798144, "elapsedSeconds": 72.5391892909829, "environmentStepsPerSecond": 24788.58693591053, "learningRate": 0.00012890624999999998, "loss": 7.7928827702999115, "policyLoss": -0.0010084925452247262, "valueLoss": 15.6077880859375, "entropy": 1.0002748742699623, "approximateKl": 0.0005183768153074197, "clipFraction": 0.0, "explainedVariance": 0.6607884622687192, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 26449, "recentEpisodeCount": 100, "recentReturnMean": 127.21182613873724, "recentReturnMedian": 129.3485098958481, "recentLengthMean": 54.9, "recentLandingRate": 0.99 }, { "update": 440, "trainingStep": 1802240, "elapsedSeconds": 72.70660716597922, "environmentStepsPerSecond": 24787.843502114367, "learningRate": 0.00012851562499999997, "loss": 39.09014344215393, "policyLoss": -0.0003751296317204833, "valueLoss": 78.20101881027222, "entropy": 0.9991098754107952, "approximateKl": 6.433307135012001e-05, "clipFraction": 0.0, "explainedVariance": 0.1858032740980371, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 26524, "recentEpisodeCount": 100, "recentReturnMean": 125.04850564536954, "recentReturnMedian": 129.61997379688546, "recentLengthMean": 55.06, "recentLandingRate": 0.98 }, { "update": 441, "trainingStep": 1806336, "elapsedSeconds": 72.87010954099242, "environmentStepsPerSecond": 24788.435359547006, "learningRate": 0.000128125, "loss": 8.295084476470947, "policyLoss": -0.0003385582531336695, "valueLoss": 16.61069691181183, "entropy": 0.9925398081541061, "approximateKl": 0.00036024842847837135, "clipFraction": 0.0, "explainedVariance": 0.6382304913457426, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 26601, "recentEpisodeCount": 100, "recentReturnMean": 128.97082778377455, "recentReturnMedian": 129.213381503243, "recentLengthMean": 53.71, "recentLandingRate": 1.0 }, { "update": 442, "trainingStep": 1810432, "elapsedSeconds": 73.04204266599845, "environmentStepsPerSecond": 24786.163337170306, "learningRate": 0.000127734375, "loss": 7.53120681643486, "policyLoss": -0.0006836539250798523, "valueLoss": 15.083617389202118, "entropy": 0.9918115101754665, "approximateKl": 0.00044061125663574785, "clipFraction": 0.0, "explainedVariance": 0.6838762071159745, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 26678, "recentEpisodeCount": 100, "recentReturnMean": 129.36222248939782, "recentReturnMedian": 129.5985908950679, "recentLengthMean": 53.39, "recentLandingRate": 1.0 }, { "update": 443, "trainingStep": 1814528, "elapsedSeconds": 73.20612937500118, "environmentStepsPerSecond": 24786.558386457113, "learningRate": 0.00012734375, "loss": 46.64174258708954, "policyLoss": -0.0007153557380661368, "valueLoss": 93.30486369132996, "entropy": 0.9973709359765053, "approximateKl": 0.0004058033155160956, "clipFraction": 0.0, "explainedVariance": 0.15763156522041122, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 26752, "recentEpisodeCount": 100, "recentReturnMean": 125.48710225493079, "recentReturnMedian": 129.79550495138392, "recentLengthMean": 53.22, "recentLandingRate": 0.98 }, { "update": 444, "trainingStep": 1818624, "elapsedSeconds": 73.37583662499674, "environmentStepsPerSecond": 24785.053004498957, "learningRate": 0.000126953125, "loss": 43.821004986763, "policyLoss": -0.002580301952548325, "valueLoss": 87.66654944419861, "entropy": 0.9689264371991158, "approximateKl": 0.0018058967834804207, "clipFraction": 0.01361083984375, "explainedVariance": 0.18112020197974366, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 26829, "recentEpisodeCount": 100, "recentReturnMean": 122.82784624889231, "recentReturnMedian": 129.29709213715978, "recentLengthMean": 55.32, "recentLandingRate": 0.97 }, { "update": 445, "trainingStep": 1822720, "elapsedSeconds": 73.53078508298495, "environmentStepsPerSecond": 24788.52902145578, "learningRate": 0.0001265625, "loss": 24.834272146224976, "policyLoss": -0.0004923897213302553, "valueLoss": 49.68949627876282, "entropy": 0.9983356036245823, "approximateKl": 0.0001875158995972015, "clipFraction": 0.0, "explainedVariance": 0.28953151964837853, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 26898, "recentEpisodeCount": 100, "recentReturnMean": 124.9508880059214, "recentReturnMedian": 129.49843920371495, "recentLengthMean": 54.58, "recentLandingRate": 0.98 }, { "update": 446, "trainingStep": 1826816, "elapsedSeconds": 73.68398174998583, "environmentStepsPerSecond": 24792.57983368076, "learningRate": 0.00012617187499999998, "loss": 44.00246441364288, "policyLoss": -0.0009440873691346496, "valueLoss": 88.02690291404724, "entropy": 1.0043156407773495, "approximateKl": 0.0004511251245276071, "clipFraction": 0.0, "explainedVariance": 0.183006988158676, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 26978, "recentEpisodeCount": 100, "recentReturnMean": 122.7122284034278, "recentReturnMedian": 129.22207036614418, "recentLengthMean": 54.84, "recentLandingRate": 0.97 }, { "update": 447, "trainingStep": 1830912, "elapsedSeconds": 73.83746158299618, "environmentStepsPerSecond": 24796.518741939464, "learningRate": 0.00012578125, "loss": 54.47510528564453, "policyLoss": -0.002519175483030267, "valueLoss": 108.97498226165771, "entropy": 0.9866953156888485, "approximateKl": 0.0043827326080645435, "clipFraction": 0.05572509765625, "explainedVariance": 0.1147083210184614, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 27045, "recentEpisodeCount": 100, "recentReturnMean": 122.61580882480389, "recentReturnMedian": 128.62026707292534, "recentLengthMean": 55.67, "recentLandingRate": 0.97 }, { "update": 448, "trainingStep": 1835008, "elapsedSeconds": 73.99898787497659, "environmentStepsPerSecond": 24797.744573213604, "learningRate": 0.000125390625, "loss": 7.581836938858032, "policyLoss": -0.002476096065947786, "valueLoss": 15.1884286403656, "entropy": 0.9901319891214371, "approximateKl": 0.0004508697966230102, "clipFraction": 0.001220703125, "explainedVariance": 0.5959014676218235, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 27119, "recentEpisodeCount": 100, "recentReturnMean": 126.42167014643346, "recentReturnMedian": 128.67113608820364, "recentLengthMean": 57.26, "recentLandingRate": 0.99 }, { "update": 449, "trainingStep": 1839104, "elapsedSeconds": 74.15151637498639, "environmentStepsPerSecond": 24801.97425362952, "learningRate": 0.00012499999999999998, "loss": 5.132105320692062, "policyLoss": -0.0012745878484565765, "valueLoss": 10.286931872367859, "entropy": 1.008603047579527, "approximateKl": 0.0007349985389737412, "clipFraction": 0.0, "explainedVariance": 0.7159150197426534, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 27188, "recentEpisodeCount": 100, "recentReturnMean": 128.68014651579463, "recentReturnMedian": 128.75513552490156, "recentLengthMean": 57.37, "recentLandingRate": 1.0 }, { "update": 450, "trainingStep": 1843200, "elapsedSeconds": 74.4393295829941, "environmentStepsPerSecond": 24761.104248594478, "learningRate": 0.000124609375, "loss": 13.76662102341652, "policyLoss": -0.0007988774450495839, "valueLoss": 27.55457580089569, "entropy": 0.9868036396801472, "approximateKl": 0.0007225430599646643, "clipFraction": 0.0, "explainedVariance": 0.47537938498004795, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 27266, "recentEpisodeCount": 100, "recentReturnMean": 126.68924630735754, "recentReturnMedian": 128.27156685455702, "recentLengthMean": 54.64, "recentLandingRate": 0.99 }, { "update": 451, "trainingStep": 1847296, "elapsedSeconds": 74.59338687499985, "environmentStepsPerSecond": 24764.876316658112, "learningRate": 0.00012421874999999998, "loss": 26.461535692214966, "policyLoss": -0.0002564848109614104, "valueLoss": 52.943156719207764, "entropy": 0.9786215834319592, "approximateKl": 0.00032727265352150425, "clipFraction": 0.0, "explainedVariance": 0.29032470588831516, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 27341, "recentEpisodeCount": 100, "recentReturnMean": 126.89858958236299, "recentReturnMedian": 129.33102529658936, "recentLengthMean": 53.93, "recentLandingRate": 0.99 }, { "update": 452, "trainingStep": 1851392, "elapsedSeconds": 74.74492924998049, "environmentStepsPerSecond": 24769.46621767634, "learningRate": 0.00012382812499999997, "loss": 42.47793883085251, "policyLoss": -0.0008721860940568149, "valueLoss": 84.9771603345871, "entropy": 0.9768348671495914, "approximateKl": 0.000544005411938997, "clipFraction": 0.00030517578125, "explainedVariance": 0.18592949148673488, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 27418, "recentEpisodeCount": 100, "recentReturnMean": 120.9633735908827, "recentReturnMedian": 129.57992723341158, "recentLengthMean": 53.66, "recentLandingRate": 0.96 }, { "update": 453, "trainingStep": 1855488, "elapsedSeconds": 74.90703737500007, "environmentStepsPerSecond": 24770.54312949322, "learningRate": 0.0001234375, "loss": 5.62154421210289, "policyLoss": -0.0002506692835595459, "valueLoss": 11.263417303562164, "entropy": 0.9913779571652412, "approximateKl": 0.00010527226913836785, "clipFraction": 0.0, "explainedVariance": 0.7304910466873806, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 27492, "recentEpisodeCount": 100, "recentReturnMean": 127.01921012938004, "recentReturnMedian": 129.27966101001948, "recentLengthMean": 54.46, "recentLandingRate": 0.99 }, { "update": 454, "trainingStep": 1859584, "elapsedSeconds": 75.07769466598984, "environmentStepsPerSecond": 24768.79462366325, "learningRate": 0.000123046875, "loss": 43.08733904361725, "policyLoss": -0.00021586217917501926, "valueLoss": 86.19482445716858, "entropy": 0.9857755601406097, "approximateKl": 3.3832420740509406e-05, "clipFraction": 0.0, "explainedVariance": 0.18510384087632292, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 27573, "recentEpisodeCount": 100, "recentReturnMean": 125.17989006093718, "recentReturnMedian": 129.42404060042463, "recentLengthMean": 53.67, "recentLandingRate": 0.98 }, { "update": 455, "trainingStep": 1863680, "elapsedSeconds": 75.27376812498551, "environmentStepsPerSecond": 24758.69145949386, "learningRate": 0.00012265625, "loss": 49.15504193305969, "policyLoss": -0.0002593464159872383, "valueLoss": 98.32986974716187, "entropy": 0.9633478969335556, "approximateKl": 0.00023378179685096256, "clipFraction": 6.103515625e-05, "explainedVariance": 0.14477079744640176, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 27645, "recentEpisodeCount": 100, "recentReturnMean": 125.11050518773884, "recentReturnMedian": 129.53346186608542, "recentLengthMean": 53.57, "recentLandingRate": 0.98 }, { "update": 456, "trainingStep": 1867776, "elapsedSeconds": 75.46792599998298, "environmentStepsPerSecond": 24749.268980843877, "learningRate": 0.000122265625, "loss": 44.233882784843445, "policyLoss": -0.0006205025711096823, "valueLoss": 88.48833394050598, "entropy": 0.9663984999060631, "approximateKl": 0.00033967917261179537, "clipFraction": 0.0, "explainedVariance": 0.17889785090285804, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 27723, "recentEpisodeCount": 100, "recentReturnMean": 120.5508338550062, "recentReturnMedian": 129.22967783510103, "recentLengthMean": 55.03, "recentLandingRate": 0.96 }, { "update": 457, "trainingStep": 1871872, "elapsedSeconds": 75.6436289580015, "environmentStepsPerSecond": 24745.930698794105, "learningRate": 0.000121875, "loss": 5.516879558563232, "policyLoss": -8.944876026362181e-05, "valueLoss": 11.053384602069855, "entropy": 0.9723371863365173, "approximateKl": 0.00038596722879447043, "clipFraction": 0.0, "explainedVariance": 0.7265518250294456, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 27797, "recentEpisodeCount": 100, "recentReturnMean": 129.3015121541536, "recentReturnMedian": 129.16120998124825, "recentLengthMean": 54.84, "recentLandingRate": 1.0 }, { "update": 458, "trainingStep": 1875968, "elapsedSeconds": 75.84031483298168, "environmentStepsPerSecond": 24735.762293858163, "learningRate": 0.00012148437499999998, "loss": 40.089555859565735, "policyLoss": -0.0015797412197571248, "valueLoss": 80.2018871307373, "entropy": 0.9808574467897415, "approximateKl": 0.0005428137883427553, "clipFraction": 0.00079345703125, "explainedVariance": 0.19164833243257984, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 27872, "recentEpisodeCount": 100, "recentReturnMean": 125.23634919850177, "recentReturnMedian": 129.4059368671551, "recentLengthMean": 53.64, "recentLandingRate": 0.98 }, { "update": 459, "trainingStep": 1880064, "elapsedSeconds": 76.07010591597646, "environmentStepsPerSecond": 24714.886056247014, "learningRate": 0.00012109375, "loss": 22.840856075286865, "policyLoss": -0.00022881425684317946, "valueLoss": 45.701805770397186, "entropy": 0.9818201176822186, "approximateKl": 0.00039778129576006904, "clipFraction": 0.0, "explainedVariance": 0.2990389039962237, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 27947, "recentEpisodeCount": 100, "recentReturnMean": 127.41518094796047, "recentReturnMedian": 129.33215592242777, "recentLengthMean": 55.53, "recentLandingRate": 0.99 }, { "update": 460, "trainingStep": 1884160, "elapsedSeconds": 76.3183298749791, "environmentStepsPerSecond": 24688.171283183703, "learningRate": 0.00012070312499999999, "loss": 24.43471324443817, "policyLoss": -0.00046593724982813, "valueLoss": 48.89026391506195, "entropy": 0.9952395223081112, "approximateKl": 0.0004867248244408984, "clipFraction": 0.00103759765625, "explainedVariance": 0.26732018574357064, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 28020, "recentEpisodeCount": 100, "recentReturnMean": 127.17844784337038, "recentReturnMedian": 129.3727700561285, "recentLengthMean": 54.92, "recentLandingRate": 0.99 }, { "update": 461, "trainingStep": 1888256, "elapsedSeconds": 76.56652424999629, "environmentStepsPerSecond": 24661.639254182177, "learningRate": 0.00012031249999999998, "loss": 24.083678126335144, "policyLoss": -0.0010948201379505917, "valueLoss": 48.18926227092743, "entropy": 0.9858016856014729, "approximateKl": 0.0004908039190922864, "clipFraction": 0.0, "explainedVariance": 0.2919530584221628, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 28094, "recentEpisodeCount": 100, "recentReturnMean": 127.29992958553179, "recentReturnMedian": 129.3741918131709, "recentLengthMean": 55.4, "recentLandingRate": 0.99 }, { "update": 462, "trainingStep": 1892352, "elapsedSeconds": 76.8205606249976, "environmentStepsPerSecond": 24633.40523167471, "learningRate": 0.000119921875, "loss": 4.188655316829681, "policyLoss": -0.0005189378571230918, "valueLoss": 8.39838981628418, "entropy": 1.0020668916404247, "approximateKl": 0.00031021589529700577, "clipFraction": 0.0, "explainedVariance": 0.7464899334117148, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 28166, "recentEpisodeCount": 100, "recentReturnMean": 126.93155865017063, "recentReturnMedian": 129.05631624511443, "recentLengthMean": 55.57, "recentLandingRate": 0.99 }, { "update": 463, "trainingStep": 1896448, "elapsedSeconds": 77.06683966598939, "environmentStepsPerSecond": 24607.834033668405, "learningRate": 0.00011953125, "loss": 4.602743566036224, "policyLoss": -0.0013128184218658134, "valueLoss": 9.22805780172348, "entropy": 0.9972476102411747, "approximateKl": 0.0007899413612904027, "clipFraction": 0.00018310546875, "explainedVariance": 0.7443394600800499, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 28242, "recentEpisodeCount": 100, "recentReturnMean": 128.79988693458304, "recentReturnMedian": 128.78853302495554, "recentLengthMean": 56.08, "recentLandingRate": 1.0 }, { "update": 464, "trainingStep": 1900544, "elapsedSeconds": 77.2268109159777, "environmentStepsPerSecond": 24609.8987833096, "learningRate": 0.00011914062499999998, "loss": 24.484577238559723, "policyLoss": -0.0008079944818746299, "valueLoss": 48.990588426589966, "entropy": 0.9908225163817406, "approximateKl": 0.0006787688180338591, "clipFraction": 0.00018310546875, "explainedVariance": 0.29167335322598675, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 28316, "recentEpisodeCount": 100, "recentReturnMean": 127.04112741094053, "recentReturnMedian": 128.8788271136582, "recentLengthMean": 55.64, "recentLandingRate": 0.99 }, { "update": 465, "trainingStep": 1904640, "elapsedSeconds": 77.3812487499963, "environmentStepsPerSecond": 24613.71496024211, "learningRate": 0.00011875, "loss": 24.900852262973785, "policyLoss": -0.00013042024511378258, "valueLoss": 49.82171106338501, "entropy": 0.9872998706996441, "approximateKl": 0.0003149494659737684, "clipFraction": 0.0, "explainedVariance": 0.30064151014349716, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 28388, "recentEpisodeCount": 100, "recentReturnMean": 125.23214993191122, "recentReturnMedian": 129.45942752202973, "recentLengthMean": 54.07, "recentLandingRate": 0.98 }, { "update": 466, "trainingStep": 1908736, "elapsedSeconds": 77.53290449999622, "environmentStepsPerSecond": 24618.399275885415, "learningRate": 0.00011835937499999999, "loss": 24.861277639865875, "policyLoss": -0.0006396071257768199, "valueLoss": 49.7432941198349, "entropy": 0.972998607903719, "approximateKl": 0.0002061342565866653, "clipFraction": 0.0, "explainedVariance": 0.3005571209366972, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 28470, "recentEpisodeCount": 100, "recentReturnMean": 127.1197873446779, "recentReturnMedian": 129.1113383732445, "recentLengthMean": 53.15, "recentLandingRate": 0.99 }, { "update": 467, "trainingStep": 1912832, "elapsedSeconds": 77.68388729100116, "environmentStepsPerSecond": 24623.27860647083, "learningRate": 0.00011796874999999998, "loss": 24.11101007461548, "policyLoss": -0.0015915975673124194, "valueLoss": 48.244867622852325, "entropy": 0.9832054786384106, "approximateKl": 0.001693932670605136, "clipFraction": 0.0107421875, "explainedVariance": 0.2972185726112472, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 28544, "recentEpisodeCount": 100, "recentReturnMean": 126.81547459104215, "recentReturnMedian": 129.22623280331027, "recentLengthMean": 53.22, "recentLandingRate": 0.99 }, { "update": 468, "trainingStep": 1916928, "elapsedSeconds": 77.83985979098361, "environmentStepsPerSecond": 24626.560288615045, "learningRate": 0.00011757812500000001, "loss": 41.44483423233032, "policyLoss": -0.0011548169131856412, "valueLoss": 82.91136991977692, "entropy": 0.9696632884442806, "approximateKl": 0.001005833222734509, "clipFraction": 0.00616455078125, "explainedVariance": 0.17591820902500932, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 28623, "recentEpisodeCount": 100, "recentReturnMean": 125.3929624709586, "recentReturnMedian": 129.7227360890247, "recentLengthMean": 54.16, "recentLandingRate": 0.98 }, { "update": 469, "trainingStep": 1921024, "elapsedSeconds": 78.00739445799263, "environmentStepsPerSecond": 24626.178240506175, "learningRate": 0.0001171875, "loss": 25.22071534395218, "policyLoss": -0.0001401682966388762, "valueLoss": 50.46115064620972, "entropy": 0.972001887857914, "approximateKl": 0.001650247497309465, "clipFraction": 0.00396728515625, "explainedVariance": 0.2831789859313498, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 28699, "recentEpisodeCount": 100, "recentReturnMean": 127.12480026291877, "recentReturnMedian": 129.48295505112037, "recentLengthMean": 52.44, "recentLandingRate": 0.99 }, { "update": 470, "trainingStep": 1925120, "elapsedSeconds": 78.16917412498151, "environmentStepsPerSecond": 24627.61083956195, "learningRate": 0.00011679687499999998, "loss": 64.57131814956665, "policyLoss": -0.0011031683534383774, "valueLoss": 129.1640968322754, "entropy": 0.9627436548471451, "approximateKl": 0.0006120073448983021, "clipFraction": 0.00079345703125, "explainedVariance": 0.11426120380110716, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 28775, "recentEpisodeCount": 100, "recentReturnMean": 122.67904286246254, "recentReturnMedian": 129.01035352209874, "recentLengthMean": 53.33, "recentLandingRate": 0.97 }, { "update": 471, "trainingStep": 1929216, "elapsedSeconds": 78.33449645797373, "environmentStepsPerSecond": 24627.92367644847, "learningRate": 0.00011640625, "loss": 5.180185109376907, "policyLoss": -0.0021469013881869614, "valueLoss": 10.384273707866669, "entropy": 0.9804764054715633, "approximateKl": 0.0019846402865368873, "clipFraction": 0.009521484375, "explainedVariance": 0.7287676507955714, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 28853, "recentEpisodeCount": 100, "recentReturnMean": 125.17141196612585, "recentReturnMedian": 129.29497226933017, "recentLengthMean": 53.4, "recentLandingRate": 0.98 }, { "update": 472, "trainingStep": 1933312, "elapsedSeconds": 78.48929833297734, "environmentStepsPerSecond": 24631.536286619055, "learningRate": 0.00011601562499999999, "loss": 24.943031668663025, "policyLoss": -0.0001365122152492404, "valueLoss": 49.905579686164856, "entropy": 0.9622018970549107, "approximateKl": 2.9734568670392036e-05, "clipFraction": 0.0, "explainedVariance": 0.3133595316588331, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 28932, "recentEpisodeCount": 100, "recentReturnMean": 127.32097739482415, "recentReturnMedian": 129.2990435292013, "recentLengthMean": 53.2, "recentLandingRate": 0.99 }, { "update": 473, "trainingStep": 1937408, "elapsedSeconds": 78.6426545829745, "environmentStepsPerSecond": 24635.587522746635, "learningRate": 0.00011562499999999998, "loss": 24.811254799365997, "policyLoss": -2.871348988264799e-05, "valueLoss": 49.64185380935669, "entropy": 0.9643769040703773, "approximateKl": 2.4298857169924304e-05, "clipFraction": 0.0, "explainedVariance": 0.30839786516249756, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 29008, "recentEpisodeCount": 100, "recentReturnMean": 127.71578764987036, "recentReturnMedian": 129.88642038404942, "recentLengthMean": 53.08, "recentLandingRate": 0.99 }, { "update": 474, "trainingStep": 1941504, "elapsedSeconds": 78.79523574997438, "environmentStepsPerSecond": 24639.865361410906, "learningRate": 0.00011523437500000001, "loss": 5.054072916507721, "policyLoss": -0.0003898798022419214, "valueLoss": 10.128322780132294, "entropy": 0.9698622934520245, "approximateKl": 7.014756556600332e-05, "clipFraction": 0.0, "explainedVariance": 0.773238599598103, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 29091, "recentEpisodeCount": 100, "recentReturnMean": 129.51127976107585, "recentReturnMedian": 129.71488440223038, "recentLengthMean": 52.09, "recentLandingRate": 1.0 }, { "update": 475, "trainingStep": 1945600, "elapsedSeconds": 78.94484979097615, "environmentStepsPerSecond": 24645.052909105583, "learningRate": 0.00011484375, "loss": 23.26501703262329, "policyLoss": -0.0002835933701135218, "valueLoss": 46.55020749568939, "entropy": 0.9802958332002163, "approximateKl": 0.00011947689927183092, "clipFraction": 0.0, "explainedVariance": 0.3064708618438642, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 29164, "recentEpisodeCount": 100, "recentReturnMean": 127.69169808978565, "recentReturnMedian": 129.79619239631575, "recentLengthMean": 51.85, "recentLandingRate": 0.99 }, { "update": 476, "trainingStep": 1949696, "elapsedSeconds": 79.09720604098402, "environmentStepsPerSecond": 24649.366236650254, "learningRate": 0.00011445312499999999, "loss": 24.97493267059326, "policyLoss": -0.0022478222817881033, "valueLoss": 49.973692893981934, "entropy": 0.9665742069482803, "approximateKl": 0.00114163163016201, "clipFraction": 0.00482177734375, "explainedVariance": 0.32272691718610114, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 29249, "recentEpisodeCount": 100, "recentReturnMean": 127.71816000742052, "recentReturnMedian": 129.88412528508343, "recentLengthMean": 52.45, "recentLandingRate": 0.99 }, { "update": 477, "trainingStep": 1953792, "elapsedSeconds": 79.25816479098285, "environmentStepsPerSecond": 24650.98712735122, "learningRate": 0.0001140625, "loss": 95.30656147003174, "policyLoss": -0.00010133383329957724, "valueLoss": 190.63251543045044, "entropy": 0.9595001339912415, "approximateKl": 0.00015558240920654498, "clipFraction": 0.0, "explainedVariance": 0.06368885924596779, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 29322, "recentEpisodeCount": 100, "recentReturnMean": 119.25103954991077, "recentReturnMedian": 129.49369219318032, "recentLengthMean": 52.75, "recentLandingRate": 0.95 }, { "update": 478, "trainingStep": 1957888, "elapsedSeconds": 79.430102540995, "environmentStepsPerSecond": 24649.193912213654, "learningRate": 0.00011367187499999999, "loss": 4.794473946094513, "policyLoss": -0.00034432936809025705, "valueLoss": 9.609193921089172, "entropy": 0.977876503020525, "approximateKl": 0.0001704313763184473, "clipFraction": 0.0, "explainedVariance": 0.7465413834071133, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 29402, "recentEpisodeCount": 100, "recentReturnMean": 126.90642530213576, "recentReturnMedian": 128.764102240355, "recentLengthMean": 53.18, "recentLandingRate": 0.99 }, { "update": 479, "trainingStep": 1961984, "elapsedSeconds": 79.59710891600116, "environmentStepsPerSecond": 24648.935454056278, "learningRate": 0.00011328124999999998, "loss": 44.8830463886261, "policyLoss": -0.0014235141425160691, "valueLoss": 89.78823447227478, "entropy": 0.9647120386362076, "approximateKl": 0.0019037304373341613, "clipFraction": 0.01812744140625, "explainedVariance": 0.16974669677674514, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 29476, "recentEpisodeCount": 100, "recentReturnMean": 125.03988816460559, "recentReturnMedian": 129.13181997882202, "recentLengthMean": 53.96, "recentLandingRate": 0.98 }, { "update": 480, "trainingStep": 1966080, "elapsedSeconds": 79.75654074997874, "environmentStepsPerSecond": 24651.0189824215, "learningRate": 0.000112890625, "loss": 5.133838981389999, "policyLoss": 2.5482586352154613e-05, "valueLoss": 10.287076652050018, "entropy": 0.9724749065935612, "approximateKl": 0.00022840707970317453, "clipFraction": 0.0, "explainedVariance": 0.7503939189761953, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 29557, "recentEpisodeCount": 100, "recentReturnMean": 127.30731469263876, "recentReturnMedian": 129.6970067373477, "recentLengthMean": 53.05, "recentLandingRate": 0.99 }, { "update": 481, "trainingStep": 1970176, "elapsedSeconds": 79.9114813329943, "environmentStepsPerSecond": 24654.47977106317, "learningRate": 0.0001125, "loss": 4.560278624296188, "policyLoss": -0.0004489838029257953, "valueLoss": 9.140930771827698, "entropy": 0.9737824164330959, "approximateKl": 8.215483831008896e-05, "clipFraction": 0.0, "explainedVariance": 0.7527493697055735, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 29632, "recentEpisodeCount": 100, "recentReturnMean": 129.77689251494587, "recentReturnMedian": 130.17701508663595, "recentLengthMean": 52.77, "recentLandingRate": 1.0 }, { "update": 482, "trainingStep": 1974272, "elapsedSeconds": 80.06512441599625, "environmentStepsPerSecond": 24658.326760878164, "learningRate": 0.00011210937499999999, "loss": 24.58422315120697, "policyLoss": -0.0006477215647464618, "valueLoss": 49.189019203186035, "entropy": 0.9638741165399551, "approximateKl": 5.456935105030425e-05, "clipFraction": 0.0, "explainedVariance": 0.3247101307505368, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 29713, "recentEpisodeCount": 100, "recentReturnMean": 127.53218358208831, "recentReturnMedian": 129.59377660765313, "recentLengthMean": 51.93, "recentLandingRate": 0.99 }, { "update": 483, "trainingStep": 1978368, "elapsedSeconds": 80.23293183298665, "environmentStepsPerSecond": 24657.80515310325, "learningRate": 0.00011171875, "loss": 4.335818350315094, "policyLoss": -0.0003139599139103666, "valueLoss": 8.691440016031265, "entropy": 0.9587815999984741, "approximateKl": 5.545641397475265e-05, "clipFraction": 0.0, "explainedVariance": 0.7991944292616777, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 29792, "recentEpisodeCount": 100, "recentReturnMean": 129.51250301105887, "recentReturnMedian": 129.82965443768626, "recentLengthMean": 51.99, "recentLandingRate": 1.0 }, { "update": 484, "trainingStep": 1982464, "elapsedSeconds": 80.39099704098771, "environmentStepsPerSecond": 24660.273823811785, "learningRate": 0.00011132812499999999, "loss": 4.094451680779457, "policyLoss": -0.00031793690868653357, "valueLoss": 8.20870327949524, "entropy": 0.9582047909498215, "approximateKl": 8.34751917864196e-05, "clipFraction": 0.0, "explainedVariance": 0.7400084233692199, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 29869, "recentEpisodeCount": 100, "recentReturnMean": 129.56223322880746, "recentReturnMedian": 129.60482819017489, "recentLengthMean": 52.71, "recentLandingRate": 1.0 }, { "update": 485, "trainingStep": 1986560, "elapsedSeconds": 80.5438546660007, "environmentStepsPerSecond": 24664.327380876766, "learningRate": 0.00011093749999999998, "loss": 40.21057379245758, "policyLoss": -0.0002020540996454656, "valueLoss": 80.44079399108887, "entropy": 0.9621197283267975, "approximateKl": 0.0001592408589203842, "clipFraction": 0.0, "explainedVariance": 0.1983451354914132, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 29946, "recentEpisodeCount": 100, "recentReturnMean": 125.17078327174299, "recentReturnMedian": 129.32197276887018, "recentLengthMean": 53.11, "recentLandingRate": 0.98 }, { "update": 486, "trainingStep": 1990656, "elapsedSeconds": 80.69936254099593, "environmentStepsPerSecond": 24667.555446782255, "learningRate": 0.000110546875, "loss": 5.062048971652985, "policyLoss": -0.001050360209774226, "valueLoss": 10.145436644554138, "entropy": 0.9618953317403793, "approximateKl": 0.0001828832864703145, "clipFraction": 0.0, "explainedVariance": 0.7149893793458968, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 30025, "recentEpisodeCount": 100, "recentReturnMean": 129.31662800460444, "recentReturnMedian": 129.35294439969584, "recentLengthMean": 52.6, "recentLandingRate": 1.0 }, { "update": 487, "trainingStep": 1994752, "elapsedSeconds": 80.85616195798502, "environmentStepsPerSecond": 24670.377021315027, "learningRate": 0.00011015624999999998, "loss": 24.42760306596756, "policyLoss": -0.0005019843229092658, "valueLoss": 48.87512147426605, "entropy": 0.9455607123672962, "approximateKl": 0.0005248808920441661, "clipFraction": 0.0, "explainedVariance": 0.31171402523470504, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 30103, "recentEpisodeCount": 100, "recentReturnMean": 127.05873028600269, "recentReturnMedian": 129.31178258579166, "recentLengthMean": 53.01, "recentLandingRate": 0.99 }, { "update": 488, "trainingStep": 1998848, "elapsedSeconds": 81.00984495799639, "environmentStepsPerSecond": 24674.136841471587, "learningRate": 0.00010976562499999997, "loss": 43.13283848762512, "policyLoss": -0.0004425947990966961, "valueLoss": 86.28562092781067, "entropy": 0.9529365412890911, "approximateKl": 0.00036967723644920625, "clipFraction": 6.103515625e-05, "explainedVariance": 0.19419834077280307, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 30185, "recentEpisodeCount": 100, "recentReturnMean": 125.26749120325913, "recentReturnMedian": 129.78014670465927, "recentLengthMean": 51.47, "recentLandingRate": 0.98 }, { "update": 489, "trainingStep": 2002944, "elapsedSeconds": 81.16106937499717, "environmentStepsPerSecond": 24678.62998139642, "learningRate": 0.000109375, "loss": 23.884683966636658, "policyLoss": -0.0002416130155324936, "valueLoss": 47.788696348667145, "entropy": 0.9422431588172913, "approximateKl": 0.0002930490118160378, "clipFraction": 0.0, "explainedVariance": 0.3233241027399646, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 30265, "recentEpisodeCount": 100, "recentReturnMean": 123.01515984439611, "recentReturnMedian": 129.3786099560093, "recentLengthMean": 50.32, "recentLandingRate": 0.97 }, { "update": 490, "trainingStep": 2007040, "elapsedSeconds": 81.31509145797463, "environmentStepsPerSecond": 24682.25718023426, "learningRate": 0.00010898437499999999, "loss": 3.756275475025177, "policyLoss": -2.7085538022220135e-05, "valueLoss": 7.531859874725342, "entropy": 0.9627410732209682, "approximateKl": 8.744016668060794e-06, "clipFraction": 0.0, "explainedVariance": 0.8302723319289721, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 30345, "recentEpisodeCount": 100, "recentReturnMean": 129.48501978086176, "recentReturnMedian": 129.52776567544788, "recentLengthMean": 51.23, "recentLandingRate": 1.0 }, { "update": 491, "trainingStep": 2011136, "elapsedSeconds": 81.46821345799253, "environmentStepsPerSecond": 24686.14340041963, "learningRate": 0.00010859374999999998, "loss": 42.62054657936096, "policyLoss": -0.0018293873872607946, "valueLoss": 85.26332139968872, "entropy": 0.9284711666405201, "approximateKl": 0.0014033006918907631, "clipFraction": 0.008056640625, "explainedVariance": 0.18068566802474462, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 30423, "recentEpisodeCount": 100, "recentReturnMean": 125.3437105826867, "recentReturnMedian": 129.3666043934645, "recentLengthMean": 51.68, "recentLandingRate": 0.98 }, { "update": 492, "trainingStep": 2015232, "elapsedSeconds": 81.62581395797315, "environmentStepsPerSecond": 24688.66039164506, "learningRate": 0.000108203125, "loss": 4.7381459176540375, "policyLoss": -0.00030636071460321546, "valueLoss": 9.495864868164062, "entropy": 0.9480218812823296, "approximateKl": 0.000238860106037464, "clipFraction": 0.0, "explainedVariance": 0.6771940883120983, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 30496, "recentEpisodeCount": 100, "recentReturnMean": 127.50716548015221, "recentReturnMedian": 129.85999699201477, "recentLengthMean": 51.84, "recentLandingRate": 0.99 }, { "update": 493, "trainingStep": 2019328, "elapsedSeconds": 81.78100424999138, "environmentStepsPerSecond": 24691.89536762399, "learningRate": 0.00010781249999999998, "loss": 5.057959288358688, "policyLoss": -0.0016485899104736745, "valueLoss": 10.138116419315338, "entropy": 0.9450441189110279, "approximateKl": 0.0011248462978983298, "clipFraction": 0.00506591796875, "explainedVariance": 0.641814845848837, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 30569, "recentEpisodeCount": 100, "recentReturnMean": 129.23394192313464, "recentReturnMedian": 129.11698292847723, "recentLengthMean": 52.94, "recentLandingRate": 1.0 }, { "update": 494, "trainingStep": 2023424, "elapsedSeconds": 81.93508383299923, "environmentStepsPerSecond": 24695.45285538683, "learningRate": 0.00010742187499999997, "loss": 7.963303104043007, "policyLoss": -0.0005323489895090461, "valueLoss": 15.946947485208511, "entropy": 0.9638209491968155, "approximateKl": 0.0009623833684599958, "clipFraction": 0.000244140625, "explainedVariance": 0.5943613666576266, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 30649, "recentEpisodeCount": 100, "recentReturnMean": 125.87368667495488, "recentReturnMedian": 129.2375025645597, "recentLengthMean": 56.11, "recentLandingRate": 0.98 }, { "update": 495, "trainingStep": 2027520, "elapsedSeconds": 82.09135904099094, "environmentStepsPerSecond": 24698.336386264382, "learningRate": 0.00010703125, "loss": 33.32859551906586, "policyLoss": -0.0008623371832072735, "valueLoss": 66.6780993938446, "entropy": 0.9591952413320541, "approximateKl": 0.00038238622073549777, "clipFraction": 0.0, "explainedVariance": 0.2518454056520093, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 30731, "recentEpisodeCount": 100, "recentReturnMean": 125.08188495523588, "recentReturnMedian": 129.7273826599121, "recentLengthMean": 50.92, "recentLandingRate": 0.98 }, { "update": 496, "trainingStep": 2031616, "elapsedSeconds": 82.24482641599025, "environmentStepsPerSecond": 24702.052257052463, "learningRate": 0.00010664062499999999, "loss": 23.0749648809433, "policyLoss": -0.0007014399161562324, "valueLoss": 46.17050218582153, "entropy": 0.958485022187233, "approximateKl": 0.0003506237299006898, "clipFraction": 0.0, "explainedVariance": 0.3014203989495, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 30806, "recentEpisodeCount": 100, "recentReturnMean": 127.67650091397758, "recentReturnMedian": 130.17523703854386, "recentLengthMean": 52.09, "recentLandingRate": 0.99 }, { "update": 497, "trainingStep": 2035712, "elapsedSeconds": 82.3978500829835, "environmentStepsPerSecond": 24705.88732533457, "learningRate": 0.00010624999999999998, "loss": 63.63140344619751, "policyLoss": -0.0007353752589551732, "valueLoss": 127.28339767456055, "entropy": 0.955941841006279, "approximateKl": 0.0004137221476412378, "clipFraction": 0.0006103515625, "explainedVariance": 0.12570585865962813, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 30892, "recentEpisodeCount": 100, "recentReturnMean": 123.10816636697156, "recentReturnMedian": 129.5403974277433, "recentLengthMean": 50.63, "recentLandingRate": 0.97 }, { "update": 498, "trainingStep": 2039808, "elapsedSeconds": 82.55280512498575, "environmentStepsPerSecond": 24709.130076339752, "learningRate": 0.000105859375, "loss": 24.66194248199463, "policyLoss": -0.00028380544972606003, "valueLoss": 49.3437043428421, "entropy": 0.9625717923045158, "approximateKl": 0.0001661879250605125, "clipFraction": 0.0, "explainedVariance": 0.2925130680558464, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 30965, "recentEpisodeCount": 100, "recentReturnMean": 125.55254101123253, "recentReturnMedian": 129.64031498430995, "recentLengthMean": 51.84, "recentLandingRate": 0.98 }, { "update": 499, "trainingStep": 2043904, "elapsedSeconds": 82.70641104099923, "environmentStepsPerSecond": 24712.763790303943, "learningRate": 0.00010546874999999999, "loss": 3.4464631378650665, "policyLoss": -0.0007154453778639436, "valueLoss": 6.913499444723129, "entropy": 0.9571194127202034, "approximateKl": 0.0002316596219316125, "clipFraction": 6.103515625e-05, "explainedVariance": 0.8251012610174868, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 31050, "recentEpisodeCount": 100, "recentReturnMean": 129.40730217412047, "recentReturnMedian": 129.44913467392325, "recentLengthMean": 52.02, "recentLandingRate": 1.0 }, { "update": 500, "trainingStep": 2048000, "elapsedSeconds": 82.86080908298027, "environmentStepsPerSecond": 24716.147750247615, "learningRate": 0.00010507812499999997, "loss": 3.189958080649376, "policyLoss": -0.0003801985294558108, "valueLoss": 6.399978041648865, "entropy": 0.9650717154145241, "approximateKl": 0.0001349273370578885, "clipFraction": 0.0, "explainedVariance": 0.789602388326164, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 31122, "recentEpisodeCount": 100, "recentReturnMean": 129.72213752175273, "recentReturnMedian": 129.92437664233148, "recentLengthMean": 52.53, "recentLandingRate": 1.0 }, { "update": 501, "trainingStep": 2052096, "elapsedSeconds": 83.01559324999107, "environmentStepsPerSecond": 24719.404146403795, "learningRate": 0.0001046875, "loss": 4.053647875785828, "policyLoss": -0.00042879374814219773, "valueLoss": 8.127264499664307, "entropy": 0.9555563181638718, "approximateKl": 0.00022011294640833512, "clipFraction": 0.0, "explainedVariance": 0.7376276887139522, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 31203, "recentEpisodeCount": 100, "recentReturnMean": 129.2837186381407, "recentReturnMedian": 129.6213478227146, "recentLengthMean": 52.87, "recentLandingRate": 1.0 }, { "update": 502, "trainingStep": 2056192, "elapsedSeconds": 83.17199095798424, "environmentStepsPerSecond": 24722.168801258118, "learningRate": 0.00010429687499999999, "loss": 24.031734466552734, "policyLoss": -0.0007910285203251988, "valueLoss": 48.08419847488403, "entropy": 0.9573358707129955, "approximateKl": 0.0003574336114979815, "clipFraction": 0.0, "explainedVariance": 0.31564181669160674, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 31282, "recentEpisodeCount": 100, "recentReturnMean": 127.1990399491807, "recentReturnMedian": 129.70500715414528, "recentLengthMean": 50.75, "recentLandingRate": 0.99 }, { "update": 503, "trainingStep": 2060288, "elapsedSeconds": 83.32742324998253, "environmentStepsPerSecond": 24725.209536590726, "learningRate": 0.00010390624999999998, "loss": 65.44524121284485, "policyLoss": -0.0005386065458878875, "valueLoss": 130.91023111343384, "entropy": 0.933590542525053, "approximateKl": 0.00023980502373888157, "clipFraction": 6.103515625e-05, "explainedVariance": 0.11506010597919025, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 31363, "recentEpisodeCount": 100, "recentReturnMean": 123.25498630659786, "recentReturnMedian": 129.85163716506213, "recentLengthMean": 51.52, "recentLandingRate": 0.97 }, { "update": 504, "trainingStep": 2064384, "elapsedSeconds": 83.4840543329774, "environmentStepsPerSecond": 24727.883863500134, "learningRate": 0.000103515625, "loss": 60.660282135009766, "policyLoss": -0.0010968471178784966, "valueLoss": 121.34189939498901, "entropy": 0.9571473188698292, "approximateKl": 0.0008105982997221872, "clipFraction": 0.0023193359375, "explainedVariance": 0.13131372170713052, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 31443, "recentEpisodeCount": 100, "recentReturnMean": 120.91639519778015, "recentReturnMedian": 129.41966038421378, "recentLengthMean": 50.93, "recentLandingRate": 0.96 }, { "update": 505, "trainingStep": 2068480, "elapsedSeconds": 83.64330358299776, "environmentStepsPerSecond": 24729.774069091905, "learningRate": 0.00010312499999999999, "loss": 23.518037915229797, "policyLoss": -0.00019417234580032527, "valueLoss": 47.05528783798218, "entropy": 0.9412135221064091, "approximateKl": 0.000615431708865799, "clipFraction": 0.00030517578125, "explainedVariance": 0.3050462370644421, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 31519, "recentEpisodeCount": 100, "recentReturnMean": 127.34347517456416, "recentReturnMedian": 129.6409664277744, "recentLengthMean": 52.28, "recentLandingRate": 0.99 }, { "update": 506, "trainingStep": 2072576, "elapsedSeconds": 83.80241087498143, "environmentStepsPerSecond": 24731.6989852705, "learningRate": 0.00010273437499999997, "loss": 25.17023679614067, "policyLoss": -0.0008153715752996504, "valueLoss": 50.36055701971054, "entropy": 0.9226273559033871, "approximateKl": 0.000714027995854849, "clipFraction": 0.0001220703125, "explainedVariance": 0.31390863492950394, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 31601, "recentEpisodeCount": 100, "recentReturnMean": 125.67788469517865, "recentReturnMedian": 130.14256127478438, "recentLengthMean": 51.52, "recentLandingRate": 0.98 }, { "update": 507, "trainingStep": 2076672, "elapsedSeconds": 83.95426616599434, "environmentStepsPerSecond": 24735.753105077532, "learningRate": 0.00010234375, "loss": 24.489759147167206, "policyLoss": -9.049181244336069e-05, "valueLoss": 48.9986526966095, "entropy": 0.9476643688976765, "approximateKl": 9.260948718292639e-05, "clipFraction": 0.0, "explainedVariance": 0.305279451727712, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 31679, "recentEpisodeCount": 100, "recentReturnMean": 127.54928622493492, "recentReturnMedian": 130.11898081126856, "recentLengthMean": 51.68, "recentLandingRate": 0.99 }, { "update": 508, "trainingStep": 2080768, "elapsedSeconds": 84.10848462500144, "environmentStepsPerSecond": 24739.097479607746, "learningRate": 0.00010195312499999999, "loss": 24.36684888601303, "policyLoss": -0.0024075649853330106, "valueLoss": 48.757426381111145, "entropy": 0.9456683248281479, "approximateKl": 0.00210820575375692, "clipFraction": 0.02069091796875, "explainedVariance": 0.2988886189389245, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 31761, "recentEpisodeCount": 100, "recentReturnMean": 125.16096253038035, "recentReturnMedian": 129.75295667815953, "recentLengthMean": 50.72, "recentLandingRate": 0.98 }, { "update": 509, "trainingStep": 2084864, "elapsedSeconds": 84.2680937499972, "environmentStepsPerSecond": 24740.846828519472, "learningRate": 0.00010156249999999998, "loss": 23.680099725723267, "policyLoss": 0.00024329754523932934, "valueLoss": 47.37883001565933, "entropy": 0.9558665007352829, "approximateKl": 0.0003832858783425763, "clipFraction": 0.0, "explainedVariance": 0.3225748959589997, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 31841, "recentEpisodeCount": 100, "recentReturnMean": 127.19923973396857, "recentReturnMedian": 129.79579494823702, "recentLengthMean": 50.07, "recentLandingRate": 0.99 }, { "update": 510, "trainingStep": 2088960, "elapsedSeconds": 84.42887854098808, "environmentStepsPerSecond": 24742.245024442233, "learningRate": 0.000101171875, "loss": 3.026876389980316, "policyLoss": -0.0001768552465364337, "valueLoss": 6.07315194606781, "entropy": 0.9522677958011627, "approximateKl": 3.8842579670017585e-05, "clipFraction": 0.0, "explainedVariance": 0.8000722166901796, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 31918, "recentEpisodeCount": 100, "recentReturnMean": 127.01928060702696, "recentReturnMedian": 129.0469525004737, "recentLengthMean": 52.08, "recentLandingRate": 0.99 }, { "update": 511, "trainingStep": 2093056, "elapsedSeconds": 84.58290508299251, "environmentStepsPerSecond": 24745.61494366148, "learningRate": 0.00010078124999999999, "loss": 24.294816493988037, "policyLoss": -0.0001861979835666716, "valueLoss": 48.60900700092316, "entropy": 0.9500839300453663, "approximateKl": 5.300641350913793e-05, "clipFraction": 0.0, "explainedVariance": 0.3201732478373023, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 32000, "recentEpisodeCount": 100, "recentReturnMean": 127.11117238122183, "recentReturnMedian": 128.886681238655, "recentLengthMean": 50.86, "recentLandingRate": 0.99 }, { "update": 512, "trainingStep": 2097152, "elapsedSeconds": 84.73808762498084, "environmentStepsPerSecond": 24748.63498550041, "learningRate": 0.00010039062499999998, "loss": 23.1907217502594, "policyLoss": -0.001741796630085446, "valueLoss": 46.40365290641785, "entropy": 0.936281256377697, "approximateKl": 0.0015680553588026669, "clipFraction": 0.00933837890625, "explainedVariance": 0.3150606809020614, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 32079, "recentEpisodeCount": 100, "recentReturnMean": 127.16011141996063, "recentReturnMedian": 128.85952083719894, "recentLengthMean": 51.29, "recentLandingRate": 0.99 }, { "update": 513, "trainingStep": 2101248, "elapsedSeconds": 84.89749141599168, "environmentStepsPerSecond": 24750.413292002162, "learningRate": 0.0001, "loss": 3.3270722925662994, "policyLoss": -0.00023478464572690427, "valueLoss": 6.673690915107727, "entropy": 0.9538380019366741, "approximateKl": 0.0006537580484291539, "clipFraction": 6.103515625e-05, "explainedVariance": 0.7935508484950998, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 32158, "recentEpisodeCount": 100, "recentReturnMean": 127.46378489477404, "recentReturnMedian": 129.37875612312928, "recentLengthMean": 51.35, "recentLandingRate": 0.99 }, { "update": 514, "trainingStep": 2105344, "elapsedSeconds": 85.0606064159947, "environmentStepsPerSecond": 24751.104990995143, "learningRate": 9.9609375e-05, "loss": 46.16678190231323, "policyLoss": -0.0006892762612551451, "valueLoss": 92.35361504554749, "entropy": 0.9336318150162697, "approximateKl": 0.00027382199550629593, "clipFraction": 0.0, "explainedVariance": 0.17308010121286965, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 32239, "recentEpisodeCount": 100, "recentReturnMean": 125.30022983419708, "recentReturnMedian": 129.54261880158447, "recentLengthMean": 51.77, "recentLandingRate": 0.98 }, { "update": 515, "trainingStep": 2109440, "elapsedSeconds": 85.21548079099739, "environmentStepsPerSecond": 24754.187624355367, "learningRate": 9.921874999999998e-05, "loss": 24.738349497318268, "policyLoss": -0.0027229366241954267, "valueLoss": 49.50090456008911, "entropy": 0.9379664063453674, "approximateKl": 0.0012279775692149997, "clipFraction": 0.0081787109375, "explainedVariance": 0.30088904233040925, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 32318, "recentEpisodeCount": 100, "recentReturnMean": 123.14139644765386, "recentReturnMedian": 130.0293034517672, "recentLengthMean": 51.15, "recentLandingRate": 0.97 }, { "update": 516, "trainingStep": 2113536, "elapsedSeconds": 85.36871391598834, "environmentStepsPerSecond": 24757.735041902335, "learningRate": 9.8828125e-05, "loss": 44.722827672958374, "policyLoss": -0.00048466767475474626, "valueLoss": 89.46507120132446, "entropy": 0.9222435019910336, "approximateKl": 0.0001588115374033805, "clipFraction": 0.0, "explainedVariance": 0.193069948676735, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 32399, "recentEpisodeCount": 100, "recentReturnMean": 125.43822954337175, "recentReturnMedian": 129.5582505564671, "recentLengthMean": 50.82, "recentLandingRate": 0.98 }, { "update": 517, "trainingStep": 2117632, "elapsedSeconds": 85.52105420798762, "environmentStepsPerSecond": 24761.52825303005, "learningRate": 9.843749999999999e-05, "loss": 43.91045159101486, "policyLoss": -0.0012500998855102807, "valueLoss": 87.84182906150818, "entropy": 0.9212423525750637, "approximateKl": 0.0012907641321362462, "clipFraction": 0.00311279296875, "explainedVariance": 0.19123983304606684, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 32481, "recentEpisodeCount": 100, "recentReturnMean": 125.37643421107437, "recentReturnMedian": 129.5582505564671, "recentLengthMean": 50.53, "recentLandingRate": 0.98 }, { "update": 518, "trainingStep": 2121728, "elapsedSeconds": 85.68855795799755, "environmentStepsPerSecond": 24760.925502329257, "learningRate": 9.804687499999998e-05, "loss": 3.4289966970682144, "policyLoss": 0.0003262403479311615, "valueLoss": 6.875882983207703, "entropy": 0.9271035492420197, "approximateKl": 0.00018013637600233778, "clipFraction": 0.0, "explainedVariance": 0.8440408601446479, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 32563, "recentEpisodeCount": 100, "recentReturnMean": 129.79097548780453, "recentReturnMedian": 130.0146410302259, "recentLengthMean": 50.09, "recentLandingRate": 1.0 }, { "update": 519, "trainingStep": 2125824, "elapsedSeconds": 85.85294524999335, "environmentStepsPerSecond": 24761.223902218597, "learningRate": 9.765625e-05, "loss": 3.48904225230217, "policyLoss": -0.00027687106921803206, "valueLoss": 6.99732369184494, "entropy": 0.9342673346400261, "approximateKl": 3.843635931843892e-05, "clipFraction": 0.0, "explainedVariance": 0.8064175618992733, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 32642, "recentEpisodeCount": 100, "recentReturnMean": 130.04594063090835, "recentReturnMedian": 130.15872671455145, "recentLengthMean": 50.69, "recentLandingRate": 1.0 }, { "update": 520, "trainingStep": 2129920, "elapsedSeconds": 86.00889991599252, "environmentStepsPerSecond": 24763.948871341887, "learningRate": 9.7265625e-05, "loss": 24.531632781028748, "policyLoss": -0.0012172925926279277, "valueLoss": 49.08438301086426, "entropy": 0.9341119155287743, "approximateKl": 0.0009523915978206787, "clipFraction": 0.0057373046875, "explainedVariance": 0.2854253721173783, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 32718, "recentEpisodeCount": 100, "recentReturnMean": 128.14254696695528, "recentReturnMedian": 130.45403988705948, "recentLengthMean": 51.77, "recentLandingRate": 0.99 }, { "update": 521, "trainingStep": 2134016, "elapsedSeconds": 86.16386141598923, "environmentStepsPerSecond": 24766.949448762698, "learningRate": 9.687499999999998e-05, "loss": 3.161164864897728, "policyLoss": -0.00040498911403119564, "valueLoss": 6.341844141483307, "entropy": 0.9352265894412994, "approximateKl": 0.0008645033376524225, "clipFraction": 0.00103759765625, "explainedVariance": 0.8311939888877595, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 32804, "recentEpisodeCount": 100, "recentReturnMean": 127.55718233417603, "recentReturnMedian": 129.49447742904886, "recentLengthMean": 51.03, "recentLandingRate": 0.99 }, { "update": 522, "trainingStep": 2138112, "elapsedSeconds": 86.31670745799784, "environmentStepsPerSecond": 24770.546316776697, "learningRate": 9.6484375e-05, "loss": 63.98875069618225, "policyLoss": -0.0005657510337186977, "valueLoss": 127.99729585647583, "entropy": 0.9330964088439941, "approximateKl": 0.00012331178368185647, "clipFraction": 0.0, "explainedVariance": 0.1166826819388076, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 32881, "recentEpisodeCount": 100, "recentReturnMean": 123.3512502717349, "recentReturnMedian": 129.38172153569758, "recentLengthMean": 50.13, "recentLandingRate": 0.97 }, { "update": 523, "trainingStep": 2142208, "elapsedSeconds": 86.47054541599937, "environmentStepsPerSecond": 24773.846281344653, "learningRate": 9.609374999999999e-05, "loss": 62.552531480789185, "policyLoss": -0.0010768697975436226, "valueLoss": 125.12563228607178, "entropy": 0.9206977859139442, "approximateKl": 0.0011183263341081329, "clipFraction": 0.00537109375, "explainedVariance": 0.13115707380213204, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 32965, "recentEpisodeCount": 100, "recentReturnMean": 120.76120421674482, "recentReturnMedian": 129.12784110529174, "recentLengthMean": 50.09, "recentLandingRate": 0.96 }, { "update": 524, "trainingStep": 2146304, "elapsedSeconds": 86.6281062499911, "environmentStepsPerSecond": 24776.06971813747, "learningRate": 9.570312499999998e-05, "loss": 44.6609081029892, "policyLoss": -0.0007078889757394791, "valueLoss": 89.34151697158813, "entropy": 0.9143134243786335, "approximateKl": 0.0003862515513901599, "clipFraction": 0.0, "explainedVariance": 0.17718091193450025, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 33045, "recentEpisodeCount": 100, "recentReturnMean": 124.8656136712349, "recentReturnMedian": 129.67232722835615, "recentLengthMean": 50.14, "recentLandingRate": 0.98 }, { "update": 525, "trainingStep": 2150400, "elapsedSeconds": 86.7839964159939, "environmentStepsPerSecond": 24778.762085260354, "learningRate": 9.53125e-05, "loss": 3.6571920067071915, "policyLoss": 0.0001532132737338543, "valueLoss": 7.33276030421257, "entropy": 0.9341374933719635, "approximateKl": 0.0006671272130915895, "clipFraction": 0.0, "explainedVariance": 0.8173691754977069, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 33125, "recentEpisodeCount": 100, "recentReturnMean": 129.32308339110722, "recentReturnMedian": 129.45835139858536, "recentLengthMean": 50.49, "recentLandingRate": 1.0 }, { "update": 526, "trainingStep": 2154496, "elapsedSeconds": 86.97195737497532, "environmentStepsPerSecond": 24772.306672494404, "learningRate": 9.4921875e-05, "loss": 23.77976793050766, "policyLoss": -0.000852113647852093, "valueLoss": 47.58004653453827, "entropy": 0.9403059780597687, "approximateKl": 0.0001622650343051646, "clipFraction": 0.0, "explainedVariance": 0.3266523793050734, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 33205, "recentEpisodeCount": 100, "recentReturnMean": 127.0223669500887, "recentReturnMedian": 129.37759607471526, "recentLengthMean": 50.57, "recentLandingRate": 0.99 }, { "update": 527, "trainingStep": 2158592, "elapsedSeconds": 87.1289048329927, "environmentStepsPerSecond": 24774.69450738024, "learningRate": 9.453124999999998e-05, "loss": 24.078296571969986, "policyLoss": -0.0010026656673289835, "valueLoss": 48.17738902568817, "entropy": 0.9395206309854984, "approximateKl": 0.0007386353827314451, "clipFraction": 0.0015869140625, "explainedVariance": 0.2943060740122918, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 33284, "recentEpisodeCount": 100, "recentReturnMean": 125.18936513665241, "recentReturnMedian": 129.71612768512568, "recentLengthMean": 51.21, "recentLandingRate": 0.98 }, { "update": 528, "trainingStep": 2162688, "elapsedSeconds": 87.28807470799075, "environmentStepsPerSecond": 24776.442913135048, "learningRate": 9.4140625e-05, "loss": 3.128226637840271, "policyLoss": -3.465492045506835e-05, "valueLoss": 6.27494540810585, "entropy": 0.9211420565843582, "approximateKl": 0.0001736794838507194, "clipFraction": 0.0, "explainedVariance": 0.8299842575279777, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 33368, "recentEpisodeCount": 100, "recentReturnMean": 129.46778288648164, "recentReturnMedian": 129.79075398982968, "recentLengthMean": 50.74, "recentLandingRate": 1.0 }, { "update": 529, "trainingStep": 2166784, "elapsedSeconds": 87.4483687079919, "environmentStepsPerSecond": 24777.86643722695, "learningRate": 9.374999999999999e-05, "loss": 2.5683362185955048, "policyLoss": -0.0004660628910642117, "valueLoss": 5.156540364027023, "entropy": 0.9467899054288864, "approximateKl": 9.557870725984685e-05, "clipFraction": 0.0, "explainedVariance": 0.8369063060728962, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 33446, "recentEpisodeCount": 100, "recentReturnMean": 129.26522532206334, "recentReturnMedian": 129.32940304698423, "recentLengthMean": 50.14, "recentLandingRate": 1.0 }, { "update": 530, "trainingStep": 2170880, "elapsedSeconds": 87.61684745797538, "environmentStepsPerSecond": 24776.969989033703, "learningRate": 9.335937499999998e-05, "loss": 45.15680801868439, "policyLoss": -0.0006618203915422782, "valueLoss": 90.33361458778381, "entropy": 0.9338131807744503, "approximateKl": 8.172023080987856e-05, "clipFraction": 0.0, "explainedVariance": 0.1807108802546582, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 33527, "recentEpisodeCount": 100, "recentReturnMean": 125.17338901418393, "recentReturnMedian": 129.31536783045158, "recentLengthMean": 50.18, "recentLandingRate": 0.98 }, { "update": 531, "trainingStep": 2174976, "elapsedSeconds": 87.77202945799218, "environmentStepsPerSecond": 24779.83035633176, "learningRate": 9.296875e-05, "loss": 23.22320705652237, "policyLoss": -0.0005407615681178868, "valueLoss": 46.466289043426514, "entropy": 0.9397084005177021, "approximateKl": 0.00018328709120396525, "clipFraction": 0.0, "explainedVariance": 0.31781056006698094, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 33608, "recentEpisodeCount": 100, "recentReturnMean": 127.40659696666698, "recentReturnMedian": 129.57976914173923, "recentLengthMean": 50.74, "recentLandingRate": 0.99 }, { "update": 532, "trainingStep": 2179072, "elapsedSeconds": 87.93590783298714, "environmentStepsPerSecond": 24780.22975709328, "learningRate": 9.2578125e-05, "loss": 2.847498670220375, "policyLoss": -9.10580565687269e-05, "valueLoss": 5.713908433914185, "entropy": 0.9364516735076904, "approximateKl": 0.00019036712183151394, "clipFraction": 0.0, "explainedVariance": 0.8050176666876926, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 33686, "recentEpisodeCount": 100, "recentReturnMean": 129.0456151003872, "recentReturnMedian": 129.15129008051008, "recentLengthMean": 51.51, "recentLandingRate": 1.0 }, { "update": 533, "trainingStep": 2183168, "elapsedSeconds": 88.10006991599221, "environmentStepsPerSecond": 24780.547871094303, "learningRate": 9.218749999999998e-05, "loss": 46.10771298408508, "policyLoss": -0.000790634861914441, "valueLoss": 92.23568820953369, "entropy": 0.9341180622577667, "approximateKl": 0.0001397347659803927, "clipFraction": 0.0, "explainedVariance": 0.15633363481479923, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 33770, "recentEpisodeCount": 100, "recentReturnMean": 124.96908657431922, "recentReturnMedian": 129.08458675909787, "recentLengthMean": 52.13, "recentLandingRate": 0.98 }, { "update": 534, "trainingStep": 2187264, "elapsedSeconds": 88.25881449997541, "environmentStepsPerSecond": 24782.385899831108, "learningRate": 9.1796875e-05, "loss": 12.646156042814255, "policyLoss": -0.0002374346659053117, "valueLoss": 25.311679482460022, "entropy": 0.944646880030632, "approximateKl": 0.00011022482794942334, "clipFraction": 0.0, "explainedVariance": 0.46436684487538216, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 33848, "recentEpisodeCount": 100, "recentReturnMean": 124.86211771778515, "recentReturnMedian": 128.84390521348178, "recentLengthMean": 50.3, "recentLandingRate": 0.98 }, { "update": 535, "trainingStep": 2191360, "elapsedSeconds": 88.4434380409948, "environmentStepsPerSecond": 24776.965352525905, "learningRate": 9.140624999999999e-05, "loss": 25.527248173952103, "policyLoss": -0.0007012064743321389, "valueLoss": 51.07422482967377, "entropy": 0.9163599461317062, "approximateKl": 0.00021180241310503334, "clipFraction": 6.103515625e-05, "explainedVariance": 0.29214943229050594, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 33929, "recentEpisodeCount": 100, "recentReturnMean": 125.1291564612242, "recentReturnMedian": 129.17606641771272, "recentLengthMean": 51.07, "recentLandingRate": 0.98 }, { "update": 536, "trainingStep": 2195456, "elapsedSeconds": 88.63090499999817, "environmentStepsPerSecond": 24770.772677995847, "learningRate": 9.101562499999998e-05, "loss": 2.864926055073738, "policyLoss": 0.0001712151279207319, "valueLoss": 5.74803814291954, "entropy": 0.9264205135405064, "approximateKl": 0.00015234020975185558, "clipFraction": 0.0, "explainedVariance": 0.8076353277809991, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 34010, "recentEpisodeCount": 100, "recentReturnMean": 129.3842082626561, "recentReturnMedian": 129.09829193202313, "recentLengthMean": 51.55, "recentLandingRate": 1.0 }, { "update": 537, "trainingStep": 2199552, "elapsedSeconds": 88.79888974997448, "environmentStepsPerSecond": 24770.039424965133, "learningRate": 9.062500000000001e-05, "loss": 64.35757827758789, "policyLoss": -0.0001519909710623324, "valueLoss": 128.73424911499023, "entropy": 0.9393527396023273, "approximateKl": 5.1974038797197863e-05, "clipFraction": 0.0, "explainedVariance": 0.1022328445459263, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 34087, "recentEpisodeCount": 100, "recentReturnMean": 122.95485904717411, "recentReturnMedian": 129.2954088789411, "recentLengthMean": 50.95, "recentLandingRate": 0.97 }, { "update": 538, "trainingStep": 2203648, "elapsedSeconds": 88.96624895799323, "environmentStepsPerSecond": 24769.48309960203, "learningRate": 9.0234375e-05, "loss": 40.85916745662689, "policyLoss": -0.000704937323462218, "valueLoss": 81.73851561546326, "entropy": 0.9385308660566807, "approximateKl": 0.00034124070225516334, "clipFraction": 0.0, "explainedVariance": 0.17332489801544426, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 34167, "recentEpisodeCount": 100, "recentReturnMean": 124.8315368421915, "recentReturnMedian": 128.94132638769224, "recentLengthMean": 52.12, "recentLandingRate": 0.98 }, { "update": 539, "trainingStep": 2207744, "elapsedSeconds": 89.12432987499051, "environmentStepsPerSecond": 24771.507433454743, "learningRate": 8.984374999999998e-05, "loss": 43.08133947849274, "policyLoss": -0.0003767457092180848, "valueLoss": 86.18230175971985, "entropy": 0.9434532560408115, "approximateKl": 9.835523087531328e-05, "clipFraction": 0.0, "explainedVariance": 0.1788691628951644, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 34250, "recentEpisodeCount": 100, "recentReturnMean": 124.97103424890011, "recentReturnMedian": 129.4386221440509, "recentLengthMean": 51.51, "recentLandingRate": 0.98 }, { "update": 540, "trainingStep": 2211840, "elapsedSeconds": 89.32032820797758, "environmentStepsPerSecond": 24763.007977868707, "learningRate": 8.9453125e-05, "loss": 1.6840408369898796, "policyLoss": -0.0003488481743261218, "valueLoss": 3.387797310948372, "entropy": 0.9508956857025623, "approximateKl": 0.0003269282533437945, "clipFraction": 0.0, "explainedVariance": 0.878527564869113, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 34329, "recentEpisodeCount": 100, "recentReturnMean": 128.79577240251876, "recentReturnMedian": 129.41630784235895, "recentLengthMean": 50.91, "recentLandingRate": 1.0 }, { "update": 541, "trainingStep": 2215936, "elapsedSeconds": 89.52901645799284, "environmentStepsPerSecond": 24751.03701200293, "learningRate": 8.906249999999999e-05, "loss": 3.525653585791588, "policyLoss": -0.0011500156251713634, "valueLoss": 7.072315752506256, "entropy": 0.9354254864156246, "approximateKl": 0.00026381136194686405, "clipFraction": 0.0, "explainedVariance": 0.7477116413517713, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 34407, "recentEpisodeCount": 100, "recentReturnMean": 129.11135020601316, "recentReturnMedian": 129.44076142902486, "recentLengthMean": 52.29, "recentLandingRate": 1.0 }, { "update": 542, "trainingStep": 2220032, "elapsedSeconds": 89.71312287499313, "environmentStepsPerSecond": 24745.900363912286, "learningRate": 8.867187499999998e-05, "loss": 3.582570195198059, "policyLoss": -0.0001886358659248799, "valueLoss": 7.184238702058792, "entropy": 0.9360561221837997, "approximateKl": 0.00017600981300347485, "clipFraction": 0.0, "explainedVariance": 0.7583306597562774, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 34484, "recentEpisodeCount": 100, "recentReturnMean": 129.63797385064768, "recentReturnMedian": 129.86293879617006, "recentLengthMean": 52.01, "recentLandingRate": 1.0 }, { "update": 543, "trainingStep": 2224128, "elapsedSeconds": 89.87445408297936, "environmentStepsPerSecond": 24747.05435146794, "learningRate": 8.828125000000001e-05, "loss": 19.536294355988503, "policyLoss": -0.0003949904057662934, "valueLoss": 39.092127591371536, "entropy": 0.9374453946948051, "approximateKl": 0.0005218562146183103, "clipFraction": 6.103515625e-05, "explainedVariance": 0.3493666282581278, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 34566, "recentEpisodeCount": 100, "recentReturnMean": 127.64052783786491, "recentReturnMedian": 129.66358294012025, "recentLengthMean": 51.13, "recentLandingRate": 0.99 }, { "update": 544, "trainingStep": 2228224, "elapsedSeconds": 90.03341833298327, "environmentStepsPerSecond": 24748.854828093336, "learningRate": 8.7890625e-05, "loss": 24.074632585048676, "policyLoss": -9.532098192721605e-05, "valueLoss": 48.167983055114746, "entropy": 0.9263398386538029, "approximateKl": 0.00013596053395303898, "clipFraction": 0.0, "explainedVariance": 0.31436411974422307, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 34650, "recentEpisodeCount": 100, "recentReturnMean": 127.15102491198701, "recentReturnMedian": 129.58783380394743, "recentLengthMean": 49.77, "recentLandingRate": 0.99 }, { "update": 545, "trainingStep": 2232320, "elapsedSeconds": 90.19230699999025, "environmentStepsPerSecond": 24750.669699581376, "learningRate": 8.749999999999999e-05, "loss": 97.93386602401733, "policyLoss": -1.824002538342029e-05, "valueLoss": 195.88627910614014, "entropy": 0.9252736158668995, "approximateKl": 0.0001039583730744198, "clipFraction": 0.0, "explainedVariance": 0.0610442369738351, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 34730, "recentEpisodeCount": 100, "recentReturnMean": 118.95837458373157, "recentReturnMedian": 129.3992741839029, "recentLengthMean": 50.76, "recentLandingRate": 0.95 }, { "update": 546, "trainingStep": 2236416, "elapsedSeconds": 90.35476550000021, "environmentStepsPerSecond": 24751.50024046042, "learningRate": 8.7109375e-05, "loss": 26.905673265457153, "policyLoss": -0.000752142834244296, "valueLoss": 53.83107507228851, "entropy": 0.9112160466611385, "approximateKl": 0.0003249866967962589, "clipFraction": 0.0, "explainedVariance": 0.24713048062733156, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 34804, "recentEpisodeCount": 100, "recentReturnMean": 123.0628620864835, "recentReturnMedian": 129.7078777330462, "recentLengthMean": 51.77, "recentLandingRate": 0.97 }, { "update": 547, "trainingStep": 2240512, "elapsedSeconds": 90.51320095799747, "environmentStepsPerSecond": 24753.427967260894, "learningRate": 8.671874999999999e-05, "loss": 113.8976411819458, "policyLoss": -0.000617606652667746, "valueLoss": 227.81456851959229, "entropy": 0.9025793224573135, "approximateKl": 0.0002637734323798213, "clipFraction": 0.0, "explainedVariance": 0.04785938023432024, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 34885, "recentEpisodeCount": 100, "recentReturnMean": 114.8220579977546, "recentReturnMedian": 130.23222642368637, "recentLengthMean": 52.42, "recentLandingRate": 0.93 }, { "update": 548, "trainingStep": 2244608, "elapsedSeconds": 90.66776841599494, "environmentStepsPerSecond": 24756.405051257694, "learningRate": 8.632812499999998e-05, "loss": 48.76078009605408, "policyLoss": -4.231440834701061e-05, "valueLoss": 97.54016947746277, "entropy": 0.9262395761907101, "approximateKl": 1.1195959814358503e-05, "clipFraction": 0.0, "explainedVariance": 0.16804424851165656, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 34966, "recentEpisodeCount": 100, "recentReturnMean": 121.05025742598525, "recentReturnMedian": 129.53900518082082, "recentLengthMean": 52.25, "recentLandingRate": 0.96 }, { "update": 549, "trainingStep": 2248704, "elapsedSeconds": 90.82486479097861, "environmentStepsPerSecond": 24758.682604979313, "learningRate": 8.593750000000001e-05, "loss": 4.542121276259422, "policyLoss": -0.0004429894033819437, "valueLoss": 9.103792667388916, "entropy": 0.9332079105079174, "approximateKl": 4.71313287562225e-05, "clipFraction": 0.0, "explainedVariance": 0.6940384371494073, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 35044, "recentEpisodeCount": 100, "recentReturnMean": 127.16049406968203, "recentReturnMedian": 129.28109978273278, "recentLengthMean": 51.84, "recentLandingRate": 0.99 }, { "update": 550, "trainingStep": 2252800, "elapsedSeconds": 90.98290258299676, "environmentStepsPerSecond": 24760.69608732193, "learningRate": 8.5546875e-05, "loss": 27.98303997516632, "policyLoss": -0.0005514234653674066, "valueLoss": 55.98587381839752, "entropy": 0.9345737248659134, "approximateKl": 0.00018063107563648373, "clipFraction": 0.0, "explainedVariance": 0.22865874340400671, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 35119, "recentEpisodeCount": 100, "recentReturnMean": 127.53596914252266, "recentReturnMedian": 129.72696727747098, "recentLengthMean": 51.3, "recentLandingRate": 0.99 }, { "update": 551, "trainingStep": 2256896, "elapsedSeconds": 91.13649612499285, "environmentStepsPerSecond": 24763.91013436251, "learningRate": 8.515624999999999e-05, "loss": 23.674591422080994, "policyLoss": -0.0016819183656480163, "valueLoss": 47.370901584625244, "entropy": 0.917728379368782, "approximateKl": 0.00046660847146995366, "clipFraction": 0.00030517578125, "explainedVariance": 0.3124897635750381, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 35202, "recentEpisodeCount": 100, "recentReturnMean": 127.1766322496906, "recentReturnMedian": 129.57991719152778, "recentLengthMean": 54.33, "recentLandingRate": 0.99 }, { "update": 552, "trainingStep": 2260992, "elapsedSeconds": 91.28903733298648, "environmentStepsPerSecond": 24767.398869075496, "learningRate": 8.4765625e-05, "loss": 2.5147121995687485, "policyLoss": 0.0010678567923605442, "valueLoss": 5.0457490384578705, "entropy": 0.9230150133371353, "approximateKl": 0.00043457562060211785, "clipFraction": 6.103515625e-05, "explainedVariance": 0.859246334271017, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 35283, "recentEpisodeCount": 100, "recentReturnMean": 129.7605776073484, "recentReturnMedian": 130.22502663686464, "recentLengthMean": 49.71, "recentLandingRate": 1.0 }, { "update": 553, "trainingStep": 2265088, "elapsedSeconds": 91.43896770797437, "environmentStepsPerSecond": 24771.583240461958, "learningRate": 8.437499999999999e-05, "loss": 22.898141980171204, "policyLoss": -0.0013872838753741235, "valueLoss": 45.817883759737015, "entropy": 0.9412385858595371, "approximateKl": 0.0003624377895903308, "clipFraction": 0.00030517578125, "explainedVariance": 0.31522441868673445, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 35362, "recentEpisodeCount": 100, "recentReturnMean": 127.79888251819098, "recentReturnMedian": 129.95493364077993, "recentLengthMean": 50.13, "recentLandingRate": 0.99 }, { "update": 554, "trainingStep": 2269184, "elapsedSeconds": 91.59172074997332, "environmentStepsPerSecond": 24774.9903748878, "learningRate": 8.398437499999998e-05, "loss": 16.85385873913765, "policyLoss": -0.0014570324856322259, "valueLoss": 33.729348570108414, "entropy": 0.9358667731285095, "approximateKl": 0.0008414166404691059, "clipFraction": 0.0028076171875, "explainedVariance": 0.3915373946100338, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 35444, "recentEpisodeCount": 100, "recentReturnMean": 127.51443746073095, "recentReturnMedian": 129.69453576696105, "recentLengthMean": 51.44, "recentLandingRate": 0.99 }, { "update": 555, "trainingStep": 2273280, "elapsedSeconds": 91.74368754099123, "environmentStepsPerSecond": 24778.59851648425, "learningRate": 8.359375000000001e-05, "loss": 1.8327554687857628, "policyLoss": -0.0008125296444632113, "valueLoss": 3.6859727948904037, "entropy": 0.9418420791625977, "approximateKl": 0.00043655129047692753, "clipFraction": 0.0, "explainedVariance": 0.8623565327475707, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 35520, "recentEpisodeCount": 100, "recentReturnMean": 129.43587896215192, "recentReturnMedian": 129.62569998204708, "recentLengthMean": 51.64, "recentLandingRate": 1.0 }, { "update": 556, "trainingStep": 2277376, "elapsedSeconds": 91.894718208001, "environmentStepsPerSecond": 24782.44717879461, "learningRate": 8.3203125e-05, "loss": 19.96889027953148, "policyLoss": -0.0005217170692048967, "valueLoss": 39.95786154270172, "entropy": 0.9518792815506458, "approximateKl": 0.0005396507403929718, "clipFraction": 0.0001220703125, "explainedVariance": 0.3177571475243609, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 35601, "recentEpisodeCount": 100, "recentReturnMean": 127.02557627973984, "recentReturnMedian": 129.17786108423024, "recentLengthMean": 52.03, "recentLandingRate": 0.99 }, { "update": 557, "trainingStep": 2281472, "elapsedSeconds": 92.04884112498257, "environmentStepsPerSecond": 24785.450551216072, "learningRate": 8.281249999999999e-05, "loss": 25.033028453588486, "policyLoss": -0.0015402113203890622, "valueLoss": 50.08780252933502, "entropy": 0.9332615472376347, "approximateKl": 0.0007002572383498773, "clipFraction": 0.000732421875, "explainedVariance": 0.2698278433445157, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 35677, "recentEpisodeCount": 100, "recentReturnMean": 126.59953097841077, "recentReturnMedian": 128.61782317984034, "recentLengthMean": 52.46, "recentLandingRate": 0.99 }, { "update": 558, "trainingStep": 2285568, "elapsedSeconds": 92.21570008297567, "environmentStepsPerSecond": 24785.020315883805, "learningRate": 8.2421875e-05, "loss": 22.751335501670837, "policyLoss": -0.0003910188388545066, "valueLoss": 45.52203416824341, "entropy": 0.9290721043944359, "approximateKl": 0.0002074770600302145, "clipFraction": 0.0, "explainedVariance": 0.30638902662254286, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 35756, "recentEpisodeCount": 100, "recentReturnMean": 124.69965432167548, "recentReturnMedian": 129.0644287301693, "recentLengthMean": 52.11, "recentLandingRate": 0.98 }, { "update": 559, "trainingStep": 2289664, "elapsedSeconds": 92.36931045798701, "environmentStepsPerSecond": 24788.146502851985, "learningRate": 8.203124999999999e-05, "loss": 63.79118001461029, "policyLoss": -5.362843512557447e-05, "valueLoss": 127.60084009170532, "entropy": 0.9185998663306236, "approximateKl": 5.785514440503903e-05, "clipFraction": 0.0, "explainedVariance": 0.1133888363877612, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 35839, "recentEpisodeCount": 100, "recentReturnMean": 122.67916183182562, "recentReturnMedian": 128.73357088817284, "recentLengthMean": 50.83, "recentLandingRate": 0.97 }, { "update": 560, "trainingStep": 2293760, "elapsedSeconds": 92.51921366597526, "environmentStepsPerSecond": 24792.25567438594, "learningRate": 8.164062499999998e-05, "loss": 19.005703568458557, "policyLoss": -6.592817953787744e-05, "valueLoss": 38.0304434299469, "entropy": 0.9451857544481754, "approximateKl": 2.4343284167116508e-05, "clipFraction": 0.0, "explainedVariance": 0.36594035637264855, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 35919, "recentEpisodeCount": 100, "recentReturnMean": 125.28569722271263, "recentReturnMedian": 129.7129971030954, "recentLengthMean": 51.5, "recentLandingRate": 0.98 }, { "update": 561, "trainingStep": 2297856, "elapsedSeconds": 92.67535474998294, "environmentStepsPerSecond": 24794.68253667972, "learningRate": 8.125000000000001e-05, "loss": 2.3120673149824142, "policyLoss": -0.0006682979874312878, "valueLoss": 4.644127249717712, "entropy": 0.9328020624816418, "approximateKl": 8.758459443924949e-05, "clipFraction": 0.0, "explainedVariance": 0.8377388012153519, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 35999, "recentEpisodeCount": 100, "recentReturnMean": 129.72017959010452, "recentReturnMedian": 129.96641475567594, "recentLengthMean": 51.02, "recentLandingRate": 1.0 }, { "update": 562, "trainingStep": 2301952, "elapsedSeconds": 92.83580779097974, "environmentStepsPerSecond": 24795.9494808604, "learningRate": 8.0859375e-05, "loss": 2.7580535113811493, "policyLoss": -0.0004011435521533713, "valueLoss": 5.5355866849422455, "entropy": 0.9338673911988735, "approximateKl": 0.00013569331349572167, "clipFraction": 0.0, "explainedVariance": 0.7920064419206909, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 36075, "recentEpisodeCount": 100, "recentReturnMean": 129.104191715989, "recentReturnMedian": 129.14015694148839, "recentLengthMean": 51.87, "recentLandingRate": 1.0 }, { "update": 563, "trainingStep": 2306048, "elapsedSeconds": 92.99950008298038, "environmentStepsPerSecond": 24796.348345339382, "learningRate": 8.046874999999999e-05, "loss": 43.548152923583984, "policyLoss": 0.0001324463519267738, "valueLoss": 87.11485838890076, "entropy": 0.940896924585104, "approximateKl": 4.3116870074300095e-05, "clipFraction": 0.0, "explainedVariance": 0.1840646585350566, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 36158, "recentEpisodeCount": 100, "recentReturnMean": 124.9351463349168, "recentReturnMedian": 129.21428644354455, "recentLengthMean": 52.48, "recentLandingRate": 0.98 }, { "update": 564, "trainingStep": 2310144, "elapsedSeconds": 93.15892120799981, "environmentStepsPerSecond": 24797.882693832886, "learningRate": 8.0078125e-05, "loss": 23.83942425251007, "policyLoss": -0.0008997337426990271, "valueLoss": 47.699100732803345, "entropy": 0.92264349386096, "approximateKl": 0.00044640562555287033, "clipFraction": 0.00018310546875, "explainedVariance": 0.310070251484463, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 36234, "recentEpisodeCount": 100, "recentReturnMean": 125.37756970458257, "recentReturnMedian": 129.83807323500514, "recentLengthMean": 50.72, "recentLandingRate": 0.98 }, { "update": 565, "trainingStep": 2314240, "elapsedSeconds": 93.31410770799266, "environmentStepsPerSecond": 24800.537205391694, "learningRate": 7.968749999999999e-05, "loss": 43.09093689918518, "policyLoss": -0.0012868280755355954, "valueLoss": 86.20313572883606, "entropy": 0.934345867484808, "approximateKl": 0.00036361845559440553, "clipFraction": 0.0, "explainedVariance": 0.18701288633537783, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 36315, "recentEpisodeCount": 100, "recentReturnMean": 123.45308615463873, "recentReturnMedian": 129.64858636353165, "recentLengthMean": 51.16, "recentLandingRate": 0.97 }, { "update": 566, "trainingStep": 2318336, "elapsedSeconds": 93.48104016599245, "environmentStepsPerSecond": 24800.066365151437, "learningRate": 7.929687499999998e-05, "loss": 43.46309471130371, "policyLoss": -0.0010777229617815465, "valueLoss": 86.94707918167114, "entropy": 0.9367069937288761, "approximateKl": 0.0004881894128629938, "clipFraction": 0.0, "explainedVariance": 0.18263247317458264, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 36397, "recentEpisodeCount": 100, "recentReturnMean": 124.90789308509993, "recentReturnMedian": 129.14409991446882, "recentLengthMean": 50.75, "recentLandingRate": 0.98 }, { "update": 567, "trainingStep": 2322432, "elapsedSeconds": 93.63601616598316, "environmentStepsPerSecond": 24802.763883964893, "learningRate": 7.890625000000001e-05, "loss": 22.720958352088928, "policyLoss": -0.00043624790851026773, "valueLoss": 45.46155935525894, "entropy": 0.9385458789765835, "approximateKl": 0.00024629484687466174, "clipFraction": 6.103515625e-05, "explainedVariance": 0.31173270878019144, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 36475, "recentEpisodeCount": 100, "recentReturnMean": 127.51971653955029, "recentReturnMedian": 129.60070625180379, "recentLengthMean": 51.73, "recentLandingRate": 0.99 }, { "update": 568, "trainingStep": 2326528, "elapsedSeconds": 93.79314987498219, "environmentStepsPerSecond": 24804.881839463244, "learningRate": 7.8515625e-05, "loss": 53.84809899330139, "policyLoss": -8.795982284937054e-05, "valueLoss": 107.7150559425354, "entropy": 0.9340618215501308, "approximateKl": 0.0001245989878952969, "clipFraction": 0.0, "explainedVariance": 0.14080558460334158, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 36553, "recentEpisodeCount": 100, "recentReturnMean": 122.84676338733316, "recentReturnMedian": 128.92482365720207, "recentLengthMean": 51.61, "recentLandingRate": 0.97 }, { "update": 569, "trainingStep": 2330624, "elapsedSeconds": 93.95018079099827, "environmentStepsPerSecond": 24807.01985219922, "learningRate": 7.812499999999999e-05, "loss": 22.92772001028061, "policyLoss": -0.001329002290731296, "valueLoss": 45.87666982412338, "entropy": 0.9286012537777424, "approximateKl": 0.00021425466184155084, "clipFraction": 0.00042724609375, "explainedVariance": 0.31074137814842506, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 36634, "recentEpisodeCount": 100, "recentReturnMean": 126.83809514629247, "recentReturnMedian": 128.56089221074944, "recentLengthMean": 52.21, "recentLandingRate": 0.99 }, { "update": 570, "trainingStep": 2334720, "elapsedSeconds": 94.10263679097989, "environmentStepsPerSecond": 24810.356857330826, "learningRate": 7.7734375e-05, "loss": 24.005004465579987, "policyLoss": -0.0012998264865018427, "valueLoss": 48.03142827749252, "entropy": 0.9410410933196545, "approximateKl": 0.0012938178260810673, "clipFraction": 0.0047607421875, "explainedVariance": 0.2970223081762846, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 36711, "recentEpisodeCount": 100, "recentReturnMean": 125.00099312445018, "recentReturnMedian": 129.32346080429852, "recentLengthMean": 52.16, "recentLandingRate": 0.98 }, { "update": 571, "trainingStep": 2338816, "elapsedSeconds": 94.25969808298396, "environmentStepsPerSecond": 24812.4707331543, "learningRate": 7.734374999999999e-05, "loss": 3.710288420319557, "policyLoss": -0.0006207724945852533, "valueLoss": 7.440229743719101, "entropy": 0.9205716326832771, "approximateKl": 0.0011029534798581153, "clipFraction": 0.00323486328125, "explainedVariance": 0.7421672613718948, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 36790, "recentEpisodeCount": 100, "recentReturnMean": 129.5119231040794, "recentReturnMedian": 129.7059086044319, "recentLengthMean": 51.07, "recentLandingRate": 1.0 }, { "update": 572, "trainingStep": 2342912, "elapsedSeconds": 94.41594970799633, "environmentStepsPerSecond": 24814.79037435952, "learningRate": 7.695312499999998e-05, "loss": 10.552611276507378, "policyLoss": -0.00037058856105431914, "valueLoss": 21.124325662851334, "entropy": 0.9180809259414673, "approximateKl": 0.00013195418068789877, "clipFraction": 0.0, "explainedVariance": 0.5126042729925423, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 36869, "recentEpisodeCount": 100, "recentReturnMean": 127.25125538845371, "recentReturnMedian": 129.231243141694, "recentLengthMean": 49.75, "recentLandingRate": 0.99 }, { "update": 573, "trainingStep": 2347008, "elapsedSeconds": 94.57523149999906, "environmentStepsPerSecond": 24816.307216758156, "learningRate": 7.656250000000001e-05, "loss": 3.0674761831760406, "policyLoss": -0.00019574866746552289, "valueLoss": 6.153933793306351, "entropy": 0.9294923730194569, "approximateKl": 7.818900485290214e-05, "clipFraction": 0.0, "explainedVariance": 0.7895956144669009, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 36948, "recentEpisodeCount": 100, "recentReturnMean": 129.38177944356576, "recentReturnMedian": 129.72439741995186, "recentLengthMean": 54.09, "recentLandingRate": 1.0 }, { "update": 574, "trainingStep": 2351104, "elapsedSeconds": 94.7270959999878, "environmentStepsPerSecond": 24819.762235720842, "learningRate": 7.6171875e-05, "loss": 24.504345893859863, "policyLoss": -0.0010643145069479942, "valueLoss": 49.029332756996155, "entropy": 0.9256357103586197, "approximateKl": 0.0005732690406148322, "clipFraction": 0.00030517578125, "explainedVariance": 0.29245076019093597, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 37031, "recentEpisodeCount": 100, "recentReturnMean": 127.5802674678358, "recentReturnMedian": 129.63198069110513, "recentLengthMean": 51.33, "recentLandingRate": 0.99 }, { "update": 575, "trainingStep": 2355200, "elapsedSeconds": 94.8781705829897, "environmentStepsPerSecond": 24823.41286228651, "learningRate": 7.578124999999999e-05, "loss": 3.3222422748804092, "policyLoss": -0.0004034333396703005, "valueLoss": 6.663882911205292, "entropy": 0.9295746721327305, "approximateKl": 0.0006145623483462259, "clipFraction": 0.00018310546875, "explainedVariance": 0.7707328068701069, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 37107, "recentEpisodeCount": 100, "recentReturnMean": 127.31990423859185, "recentReturnMedian": 129.4112082964275, "recentLengthMean": 50.83, "recentLandingRate": 0.99 }, { "update": 576, "trainingStep": 2359296, "elapsedSeconds": 95.03191525000148, "environmentStepsPerSecond": 24826.354323106872, "learningRate": 7.5390625e-05, "loss": 2.2855826020240784, "policyLoss": -0.00010535048204474151, "valueLoss": 4.589795261621475, "entropy": 0.9209670163691044, "approximateKl": 1.7125978047261015e-05, "clipFraction": 0.0, "explainedVariance": 0.8487136814404306, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 37192, "recentEpisodeCount": 100, "recentReturnMean": 129.71437517544894, "recentReturnMedian": 129.28943564975634, "recentLengthMean": 51.6, "recentLandingRate": 1.0 }, { "update": 577, "trainingStep": 2363392, "elapsedSeconds": 95.18136404099641, "environmentStepsPerSecond": 24830.40691644262, "learningRate": 7.5e-05, "loss": 2.1527363434433937, "policyLoss": -0.00014496734365820885, "valueLoss": 4.324424728751183, "entropy": 0.9331047832965851, "approximateKl": 3.6151428503217176e-05, "clipFraction": 0.0, "explainedVariance": 0.8568896961678656, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 37270, "recentEpisodeCount": 100, "recentReturnMean": 129.7663394933095, "recentReturnMedian": 129.8703870070167, "recentLengthMean": 50.21, "recentLandingRate": 1.0 }, { "update": 578, "trainingStep": 2367488, "elapsedSeconds": 95.33420820799074, "environmentStepsPerSecond": 24833.562312017624, "learningRate": 7.460937499999998e-05, "loss": 44.61073458194733, "policyLoss": -8.292199345305562e-05, "valueLoss": 89.240163564682, "entropy": 0.9264499880373478, "approximateKl": 1.8088572687702253e-05, "clipFraction": 0.0, "explainedVariance": 0.1624044174365763, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 37351, "recentEpisodeCount": 100, "recentReturnMean": 125.26226542918559, "recentReturnMedian": 129.50729838153347, "recentLengthMean": 51.3, "recentLandingRate": 0.98 }, { "update": 579, "trainingStep": 2371584, "elapsedSeconds": 95.4826221659896, "environmentStepsPerSecond": 24837.859981234844, "learningRate": 7.421875e-05, "loss": 1.803819939494133, "policyLoss": -0.00042217408190481365, "valueLoss": 3.627404883503914, "entropy": 0.9460315965116024, "approximateKl": 5.556188989430666e-05, "clipFraction": 0.0, "explainedVariance": 0.8809341886472386, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 37429, "recentEpisodeCount": 100, "recentReturnMean": 125.74422192000436, "recentReturnMedian": 129.6923072882928, "recentLengthMean": 50.9, "recentLandingRate": 0.98 }, { "update": 580, "trainingStep": 2375680, "elapsedSeconds": 95.6345808749902, "environmentStepsPerSecond": 24841.223522539363, "learningRate": 7.382812499999999e-05, "loss": 22.63539332151413, "policyLoss": -0.000552803830942139, "valueLoss": 45.29026806354523, "entropy": 0.9188055768609047, "approximateKl": 0.00010202117482549511, "clipFraction": 0.0, "explainedVariance": 0.308023441047363, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 37513, "recentEpisodeCount": 100, "recentReturnMean": 127.47402117697173, "recentReturnMedian": 129.71031245402992, "recentLengthMean": 51.01, "recentLandingRate": 0.99 }, { "update": 581, "trainingStep": 2379776, "elapsedSeconds": 95.78416174999438, "environmentStepsPerSecond": 24845.1931563742, "learningRate": 7.343749999999998e-05, "loss": 22.435634076595306, "policyLoss": -0.0002409379812888801, "valueLoss": 44.890228152275085, "entropy": 0.9238888993859291, "approximateKl": 0.00019829899611067958, "clipFraction": 0.0, "explainedVariance": 0.31276390055293, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 37590, "recentEpisodeCount": 100, "recentReturnMean": 125.29692470171496, "recentReturnMedian": 129.72509632539004, "recentLengthMean": 50.92, "recentLandingRate": 0.98 }, { "update": 582, "trainingStep": 2383872, "elapsedSeconds": 95.94010133299162, "environmentStepsPerSecond": 24847.50346183177, "learningRate": 7.3046875e-05, "loss": 2.2103530392050743, "policyLoss": -0.0006100013270042837, "valueLoss": 4.440341576933861, "entropy": 0.920773521065712, "approximateKl": 0.00013598514851764776, "clipFraction": 0.0, "explainedVariance": 0.8597638179444608, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 37674, "recentEpisodeCount": 100, "recentReturnMean": 127.24002444063153, "recentReturnMedian": 129.5840936927125, "recentLengthMean": 50.86, "recentLandingRate": 0.99 }, { "update": 583, "trainingStep": 2387968, "elapsedSeconds": 96.0967445409915, "environmentStepsPerSecond": 24849.624317724694, "learningRate": 7.265625e-05, "loss": 62.28804135322571, "policyLoss": 0.00010878767352551222, "valueLoss": 124.59468221664429, "entropy": 0.9408555552363396, "approximateKl": 1.721652370179072e-05, "clipFraction": 0.0, "explainedVariance": 0.11576417681125417, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 37748, "recentEpisodeCount": 100, "recentReturnMean": 122.94405970413565, "recentReturnMedian": 129.33488049171865, "recentLengthMean": 50.79, "recentLandingRate": 0.97 }, { "update": 584, "trainingStep": 2392064, "elapsedSeconds": 96.24837512499653, "environmentStepsPerSecond": 24853.032551390683, "learningRate": 7.226562499999998e-05, "loss": 22.316160947084427, "policyLoss": -0.00038653521914966404, "valueLoss": 44.651808977127075, "entropy": 0.9357023164629936, "approximateKl": 2.07456796488259e-05, "clipFraction": 0.0, "explainedVariance": 0.3522794994536922, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 37834, "recentEpisodeCount": 100, "recentReturnMean": 125.22001700712048, "recentReturnMedian": 129.42840505810454, "recentLengthMean": 50.37, "recentLandingRate": 0.98 }, { "update": 585, "trainingStep": 2396160, "elapsedSeconds": 96.40278966599726, "environmentStepsPerSecond": 24855.712249633812, "learningRate": 7.1875e-05, "loss": 2.2045838311314583, "policyLoss": -0.0005413875915110111, "valueLoss": 4.429108336567879, "entropy": 0.9428937844932079, "approximateKl": 5.5320597311947495e-05, "clipFraction": 0.0, "explainedVariance": 0.8282478038885277, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 37909, "recentEpisodeCount": 100, "recentReturnMean": 129.49561015469382, "recentReturnMedian": 129.4437555251643, "recentLengthMean": 51.17, "recentLandingRate": 1.0 }, { "update": 586, "trainingStep": 2400256, "elapsedSeconds": 96.55915329098934, "environmentStepsPerSecond": 24857.881600997694, "learningRate": 7.148437499999999e-05, "loss": 43.27757203578949, "policyLoss": -0.0003893784887623042, "valueLoss": 86.57451796531677, "entropy": 0.9297873489558697, "approximateKl": 9.178273467114195e-05, "clipFraction": 0.0, "explainedVariance": 0.19258508568776556, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 37993, "recentEpisodeCount": 100, "recentReturnMean": 124.82137234842334, "recentReturnMedian": 129.47368620033376, "recentLengthMean": 51.38, "recentLandingRate": 0.98 }, { "update": 587, "trainingStep": 2404352, "elapsedSeconds": 96.72016258299118, "environmentStepsPerSecond": 24858.849859117377, "learningRate": 7.109374999999998e-05, "loss": 74.55504274368286, "policyLoss": -0.0003352145431563258, "valueLoss": 149.1291799545288, "entropy": 0.9212292917072773, "approximateKl": 6.600969209102914e-05, "clipFraction": 0.0, "explainedVariance": 0.09623873019474649, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 38071, "recentEpisodeCount": 100, "recentReturnMean": 118.62477283609479, "recentReturnMedian": 129.3716981643811, "recentLengthMean": 51.05, "recentLandingRate": 0.95 }, { "update": 588, "trainingStep": 2408448, "elapsedSeconds": 96.87151945798541, "environmentStepsPerSecond": 24862.291966469864, "learningRate": 7.0703125e-05, "loss": 1.6667411029338837, "policyLoss": -1.073349267244339e-05, "valueLoss": 3.352074295282364, "entropy": 0.9285306856036186, "approximateKl": 6.959468009881675e-06, "clipFraction": 0.0, "explainedVariance": 0.9019618431404782, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 38155, "recentEpisodeCount": 100, "recentReturnMean": 127.2508278590523, "recentReturnMedian": 129.2787792258896, "recentLengthMean": 49.88, "recentLandingRate": 0.99 }, { "update": 589, "trainingStep": 2412544, "elapsedSeconds": 97.02873179098242, "environmentStepsPerSecond": 24864.22274586727, "learningRate": 7.03125e-05, "loss": 23.638575851917267, "policyLoss": -0.000227026961511001, "valueLoss": 47.29609298706055, "entropy": 0.9243303723633289, "approximateKl": 4.605031790561043e-05, "clipFraction": 0.0, "explainedVariance": 0.3168876133808408, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 38234, "recentEpisodeCount": 100, "recentReturnMean": 127.54027547834976, "recentReturnMedian": 129.77702526653593, "recentLengthMean": 50.61, "recentLandingRate": 0.99 }, { "update": 590, "trainingStep": 2416640, "elapsedSeconds": 97.17953795799986, "environmentStepsPerSecond": 24867.786478306272, "learningRate": 6.992187499999998e-05, "loss": 55.89536988735199, "policyLoss": -6.722932448610663e-05, "valueLoss": 111.80948805809021, "entropy": 0.930699422955513, "approximateKl": 3.078204099438153e-05, "clipFraction": 0.0, "explainedVariance": 0.13055925969933802, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 38313, "recentEpisodeCount": 100, "recentReturnMean": 122.7272037229066, "recentReturnMedian": 128.6848003938794, "recentLengthMean": 51.04, "recentLandingRate": 0.97 }, { "update": 591, "trainingStep": 2420736, "elapsedSeconds": 97.34202095799264, "environmentStepsPerSecond": 24868.355682122667, "learningRate": 6.953125e-05, "loss": 2.719337821006775, "policyLoss": -0.0003518671728670597, "valueLoss": 5.457922965288162, "entropy": 0.9271784275770187, "approximateKl": 4.211299165035598e-05, "clipFraction": 0.0, "explainedVariance": 0.803868310754283, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 38394, "recentEpisodeCount": 100, "recentReturnMean": 129.78438848621784, "recentReturnMedian": 129.789381550896, "recentLengthMean": 51.75, "recentLandingRate": 1.0 }, { "update": 592, "trainingStep": 2424832, "elapsedSeconds": 97.63645091597573, "environmentStepsPerSecond": 24835.31485681274, "learningRate": 6.914062499999999e-05, "loss": 23.195882260799408, "policyLoss": -0.0003752592019736767, "valueLoss": 46.41122579574585, "entropy": 0.9355442598462105, "approximateKl": 0.00010884742368943989, "clipFraction": 0.0, "explainedVariance": 0.32090734271244326, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 38473, "recentEpisodeCount": 100, "recentReturnMean": 126.97717469047966, "recentReturnMedian": 129.08816162124276, "recentLengthMean": 50.53, "recentLandingRate": 0.99 }, { "update": 593, "trainingStep": 2428928, "elapsedSeconds": 97.79752304099384, "environmentStepsPerSecond": 24836.293645002286, "learningRate": 6.874999999999998e-05, "loss": 2.0459456369280815, "policyLoss": -0.0007696165121160448, "valueLoss": 4.111818268895149, "entropy": 0.9193868115544319, "approximateKl": 0.00014201574231265113, "clipFraction": 0.0, "explainedVariance": 0.8806280624412735, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 38558, "recentEpisodeCount": 100, "recentReturnMean": 127.16062016288575, "recentReturnMedian": 129.22721268050373, "recentLengthMean": 49.62, "recentLandingRate": 0.99 }, { "update": 594, "trainingStep": 2433024, "elapsedSeconds": 97.96783445798792, "environmentStepsPerSecond": 24834.926825328235, "learningRate": 6.8359375e-05, "loss": 2.1124145835638046, "policyLoss": -0.0004988122964277864, "valueLoss": 4.244362637400627, "entropy": 0.9267924912273884, "approximateKl": 9.387195314047858e-05, "clipFraction": 0.0, "explainedVariance": 0.85898031310111, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 38637, "recentEpisodeCount": 100, "recentReturnMean": 129.41078546233214, "recentReturnMedian": 129.46132806013338, "recentLengthMean": 50.21, "recentLandingRate": 1.0 }, { "update": 595, "trainingStep": 2437120, "elapsedSeconds": 98.15110049999203, "environmentStepsPerSecond": 24830.28705317673, "learningRate": 6.796875e-05, "loss": 24.83958548307419, "policyLoss": -0.001796782569726929, "valueLoss": 49.70122766494751, "entropy": 0.9231324978172779, "approximateKl": 0.0008420414378633723, "clipFraction": 0.004150390625, "explainedVariance": 0.29829607795969315, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 38720, "recentEpisodeCount": 100, "recentReturnMean": 127.38316057699427, "recentReturnMedian": 129.37219690647908, "recentLengthMean": 50.8, "recentLandingRate": 0.99 }, { "update": 596, "trainingStep": 2441216, "elapsedSeconds": 98.3368403329805, "environmentStepsPerSecond": 24825.0400534911, "learningRate": 6.757812499999998e-05, "loss": 3.2782113403081894, "policyLoss": 6.313659832812846e-05, "valueLoss": 6.574788808822632, "entropy": 0.9246240481734276, "approximateKl": 0.00027801760370493867, "clipFraction": 0.0, "explainedVariance": 0.7722801282333738, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 38799, "recentEpisodeCount": 100, "recentReturnMean": 129.44738638058493, "recentReturnMedian": 129.4998340504244, "recentLengthMean": 51.87, "recentLandingRate": 1.0 }, { "update": 597, "trainingStep": 2445312, "elapsedSeconds": 98.62431012498564, "environmentStepsPerSecond": 24794.21145659807, "learningRate": 6.71875e-05, "loss": 43.39769518375397, "policyLoss": -0.000484675751067698, "valueLoss": 86.81466174125671, "entropy": 0.9150732457637787, "approximateKl": 0.00044233049266040325, "clipFraction": 0.0001220703125, "explainedVariance": 0.17944026208641817, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 38881, "recentEpisodeCount": 100, "recentReturnMean": 125.32167529336897, "recentReturnMedian": 129.1857463917695, "recentLengthMean": 50.5, "recentLandingRate": 0.98 }, { "update": 598, "trainingStep": 2449408, "elapsedSeconds": 99.1333184579853, "environmentStepsPerSecond": 24708.221595932035, "learningRate": 6.679687499999999e-05, "loss": 23.893096446990967, "policyLoss": -0.00022994683240540326, "valueLoss": 47.80487394332886, "entropy": 0.9110579490661621, "approximateKl": 4.6908928197808564e-05, "clipFraction": 0.0, "explainedVariance": 0.31577410567200515, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 38961, "recentEpisodeCount": 100, "recentReturnMean": 127.74496415689559, "recentReturnMedian": 130.21744403336197, "recentLengthMean": 49.81, "recentLandingRate": 0.99 }, { "update": 599, "trainingStep": 2453504, "elapsedSeconds": 99.30435312498594, "environmentStepsPerSecond": 24706.912867273637, "learningRate": 6.640624999999998e-05, "loss": 14.377038300037384, "policyLoss": -0.00010469218250364065, "valueLoss": 28.772479712963104, "entropy": 0.9096836894750595, "approximateKl": 0.00010374575867899694, "clipFraction": 0.0, "explainedVariance": 0.44130915782369506, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 39047, "recentEpisodeCount": 100, "recentReturnMean": 127.50962988663326, "recentReturnMedian": 129.81025487184525, "recentLengthMean": 50.14, "recentLandingRate": 0.99 }, { "update": 600, "trainingStep": 2457600, "elapsedSeconds": 99.46875124998041, "environmentStepsPerSecond": 24707.25699394446, "learningRate": 6.601562500000001e-05, "loss": 43.950427174568176, "policyLoss": 8.718925528228283e-06, "valueLoss": 87.91887164115906, "entropy": 0.9018049575388432, "approximateKl": 1.659079862292856e-05, "clipFraction": 0.0, "explainedVariance": 0.17787044323637635, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 39124, "recentEpisodeCount": 100, "recentReturnMean": 125.28955130214962, "recentReturnMedian": 130.15118734468706, "recentLengthMean": 50.49, "recentLandingRate": 0.98 }, { "update": 601, "trainingStep": 2461696, "elapsedSeconds": 99.62679287500214, "environmentStepsPerSecond": 24709.176406878763, "learningRate": 6.5625e-05, "loss": 63.32996892929077, "policyLoss": -0.00019047435489483178, "valueLoss": 126.67813539505005, "entropy": 0.8908508010208607, "approximateKl": 2.5261833798140287e-05, "clipFraction": 0.0, "explainedVariance": 0.11923781441843417, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 39206, "recentEpisodeCount": 100, "recentReturnMean": 121.00830813837871, "recentReturnMedian": 129.19099120190367, "recentLengthMean": 50.37, "recentLandingRate": 0.96 }, { "update": 602, "trainingStep": 2465792, "elapsedSeconds": 99.78491637497791, "environmentStepsPerSecond": 24711.069463984866, "learningRate": 6.523437499999998e-05, "loss": 2.7146014720201492, "policyLoss": -0.00012971946853213012, "valueLoss": 5.447568744421005, "entropy": 0.9053166434168816, "approximateKl": 9.932329703588039e-06, "clipFraction": 0.0, "explainedVariance": 0.8423446898869058, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 39290, "recentEpisodeCount": 100, "recentReturnMean": 129.43157018239262, "recentReturnMedian": 129.02930298587307, "recentLengthMean": 50.5, "recentLandingRate": 1.0 }, { "update": 603, "trainingStep": 2469888, "elapsedSeconds": 99.93881129098008, "environmentStepsPerSecond": 24714.00217888041, "learningRate": 6.484375e-05, "loss": 46.84651184082031, "policyLoss": -0.000289754883851856, "valueLoss": 93.71176242828369, "entropy": 0.90800341963768, "approximateKl": 1.399056418449618e-05, "clipFraction": 0.0, "explainedVariance": 0.16612587073270646, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 39369, "recentEpisodeCount": 100, "recentReturnMean": 122.89885258944851, "recentReturnMedian": 129.65613132498402, "recentLengthMean": 48.97, "recentLandingRate": 0.97 }, { "update": 604, "trainingStep": 2473984, "elapsedSeconds": 100.10004962497624, "environmentStepsPerSecond": 24715.112622508725, "learningRate": 6.445312499999999e-05, "loss": 3.4320446997880936, "policyLoss": -0.0002489914186298847, "valueLoss": 6.882715970277786, "entropy": 0.9064280055463314, "approximateKl": 1.371306279907003e-05, "clipFraction": 0.0, "explainedVariance": 0.7991888605557476, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 39456, "recentEpisodeCount": 100, "recentReturnMean": 129.4586973522165, "recentReturnMedian": 129.41384098381968, "recentLengthMean": 50.51, "recentLandingRate": 1.0 }, { "update": 605, "trainingStep": 2478080, "elapsedSeconds": 100.25903208297677, "environmentStepsPerSecond": 24716.775621263547, "learningRate": 6.406249999999998e-05, "loss": 24.39067769050598, "policyLoss": -0.00024996616411954165, "valueLoss": 48.79984426498413, "entropy": 0.8994767740368843, "approximateKl": 7.365836790995672e-05, "clipFraction": 0.0, "explainedVariance": 0.2981225906541658, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 39534, "recentEpisodeCount": 100, "recentReturnMean": 127.43428653917188, "recentReturnMedian": 129.47691473911982, "recentLengthMean": 50.49, "recentLandingRate": 0.99 }, { "update": 606, "trainingStep": 2482176, "elapsedSeconds": 100.4097564999829, "environmentStepsPerSecond": 24720.46628258104, "learningRate": 6.367187500000001e-05, "loss": 22.14238953590393, "policyLoss": -0.0005129333585500717, "valueLoss": 44.303961873054504, "entropy": 0.9078563824295998, "approximateKl": 0.0002073590221698396, "clipFraction": 0.0, "explainedVariance": 0.34939441645911606, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 39619, "recentEpisodeCount": 100, "recentReturnMean": 127.66087270172778, "recentReturnMedian": 130.13678651163355, "recentLengthMean": 50.35, "recentLandingRate": 0.99 }, { "update": 607, "trainingStep": 2486272, "elapsedSeconds": 100.56861441599904, "environmentStepsPerSecond": 24722.146312124885, "learningRate": 6.328125e-05, "loss": 21.210191130638123, "policyLoss": -0.0022311026114039123, "valueLoss": 42.44308030605316, "entropy": 0.9117934443056583, "approximateKl": 0.0005530752750928514, "clipFraction": 0.00152587890625, "explainedVariance": 0.33329991307131845, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 39698, "recentEpisodeCount": 100, "recentReturnMean": 127.32854281362583, "recentReturnMedian": 129.76499604200944, "recentLengthMean": 49.49, "recentLandingRate": 0.99 }, { "update": 608, "trainingStep": 2490368, "elapsedSeconds": 100.7299984159763, "environmentStepsPerSecond": 24723.201024145106, "learningRate": 6.289062499999999e-05, "loss": 39.07070589065552, "policyLoss": -0.00027623382629826665, "valueLoss": 78.16031765937805, "entropy": 0.9176503978669643, "approximateKl": 0.0003680658446683083, "clipFraction": 6.103515625e-05, "explainedVariance": 0.1985941819518231, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 39782, "recentEpisodeCount": 100, "recentReturnMean": 125.42848326783641, "recentReturnMedian": 129.8464231994003, "recentLengthMean": 50.13, "recentLandingRate": 0.98 }, { "update": 609, "trainingStep": 2494464, "elapsedSeconds": 100.89018937500077, "environmentStepsPerSecond": 24724.544729798024, "learningRate": 6.25e-05, "loss": 85.76190257072449, "policyLoss": 0.0003965927753597498, "valueLoss": 171.5410714149475, "entropy": 0.9028930179774761, "approximateKl": 0.0002445699428790249, "clipFraction": 0.0, "explainedVariance": 0.08992848920671459, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 39863, "recentEpisodeCount": 100, "recentReturnMean": 120.33154165973193, "recentReturnMedian": 128.89466953126248, "recentLengthMean": 49.38, "recentLandingRate": 0.96 }, { "update": 610, "trainingStep": 2498560, "elapsedSeconds": 101.04866574998596, "environmentStepsPerSecond": 24726.303721633725, "learningRate": 6.210937499999999e-05, "loss": 23.32009595632553, "policyLoss": -0.0006099181482568383, "valueLoss": 46.65953481197357, "entropy": 0.906153816729784, "approximateKl": 0.00014714313147123903, "clipFraction": 0.0, "explainedVariance": 0.3040010447305125, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 39943, "recentEpisodeCount": 100, "recentReturnMean": 123.14095402804192, "recentReturnMedian": 129.4951472277753, "recentLengthMean": 51.41, "recentLandingRate": 0.97 }, { "update": 611, "trainingStep": 2502656, "elapsedSeconds": 101.20374474997516, "environmentStepsPerSecond": 24728.887317192028, "learningRate": 6.171874999999998e-05, "loss": 3.562872275710106, "policyLoss": 9.460427099838853e-05, "valueLoss": 7.143793553113937, "entropy": 0.9119113311171532, "approximateKl": 0.00017345209198538214, "clipFraction": 0.0, "explainedVariance": 0.7969587187771537, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 40027, "recentEpisodeCount": 100, "recentReturnMean": 129.4769941184912, "recentReturnMedian": 129.73343721195124, "recentLengthMean": 49.8, "recentLandingRate": 1.0 }, { "update": 612, "trainingStep": 2506752, "elapsedSeconds": 101.35783195798285, "environmentStepsPerSecond": 24731.705005678847, "learningRate": 6.132812500000001e-05, "loss": 84.27472138404846, "policyLoss": -0.00023614458041265607, "valueLoss": 168.56786966323853, "entropy": 0.8976316675543785, "approximateKl": 9.209143172483891e-06, "clipFraction": 0.0, "explainedVariance": 0.0876766995719983, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 40105, "recentEpisodeCount": 100, "recentReturnMean": 120.92337365393236, "recentReturnMedian": 129.82328940881416, "recentLengthMean": 50.43, "recentLandingRate": 0.96 }, { "update": 613, "trainingStep": 2510848, "elapsedSeconds": 101.5127840829955, "environmentStepsPerSecond": 24734.303395197636, "learningRate": 6.09375e-05, "loss": 24.0302671790123, "policyLoss": -0.0007188084127847105, "valueLoss": 48.079906821250916, "entropy": 0.8967606388032436, "approximateKl": 0.0003985502989962697, "clipFraction": 0.0, "explainedVariance": 0.3000385865933025, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 40189, "recentEpisodeCount": 100, "recentReturnMean": 125.12332237364724, "recentReturnMedian": 129.32184759242227, "recentLengthMean": 50.18, "recentLandingRate": 0.98 }, { "update": 614, "trainingStep": 2514944, "elapsedSeconds": 101.69481420799275, "environmentStepsPerSecond": 24730.30723922928, "learningRate": 6.0546874999999986e-05, "loss": 3.168749302625656, "policyLoss": 0.00012773563503287733, "valueLoss": 6.3552475571632385, "entropy": 0.9002192951738834, "approximateKl": 0.00023822629009373486, "clipFraction": 0.0, "explainedVariance": 0.7894447693259456, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 40268, "recentEpisodeCount": 100, "recentReturnMean": 129.1699450031323, "recentReturnMedian": 129.3387225936167, "recentLengthMean": 50.37, "recentLandingRate": 1.0 }, { "update": 615, "trainingStep": 2519040, "elapsedSeconds": 101.86976979099563, "environmentStepsPerSecond": 24728.04253085355, "learningRate": 6.015625000000001e-05, "loss": 22.29232531785965, "policyLoss": -0.00030267040710896254, "valueLoss": 44.60338115692139, "entropy": 0.9062225669622421, "approximateKl": 6.932000178494491e-05, "clipFraction": 0.0, "explainedVariance": 0.31952680767453423, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 40351, "recentEpisodeCount": 100, "recentReturnMean": 127.47716117107265, "recentReturnMedian": 129.79016998503357, "recentLengthMean": 50.48, "recentLandingRate": 0.99 }, { "update": 616, "trainingStep": 2523136, "elapsedSeconds": 102.02997604099801, "environmentStepsPerSecond": 24729.359918561047, "learningRate": 5.9765625e-05, "loss": 3.1677711755037308, "policyLoss": 3.2348441891372204e-05, "valueLoss": 6.353672593832016, "entropy": 0.9097464233636856, "approximateKl": 5.352382140699774e-05, "clipFraction": 0.0, "explainedVariance": 0.8119493272133735, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 40436, "recentEpisodeCount": 100, "recentReturnMean": 129.8528311493252, "recentReturnMedian": 130.05578769999556, "recentLengthMean": 50.2, "recentLandingRate": 1.0 }, { "update": 617, "trainingStep": 2527232, "elapsedSeconds": 102.18428724998375, "environmentStepsPerSecond": 24732.099895332994, "learningRate": 5.9374999999999986e-05, "loss": 21.665110409259796, "policyLoss": -4.676962271332741e-05, "valueLoss": 43.348437786102295, "entropy": 0.906206201761961, "approximateKl": 5.810892616864294e-06, "clipFraction": 0.0, "explainedVariance": 0.32818143637624697, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 40515, "recentEpisodeCount": 100, "recentReturnMean": 127.60718413425202, "recentReturnMedian": 129.62291464209557, "recentLengthMean": 50.27, "recentLandingRate": 0.99 }, { "update": 618, "trainingStep": 2531328, "elapsedSeconds": 102.3431207909889, "environmentStepsPerSecond": 24733.738627822633, "learningRate": 5.898437500000001e-05, "loss": 45.45533752441406, "policyLoss": -0.00010595974163152277, "valueLoss": 90.92915439605713, "entropy": 0.9133393354713917, "approximateKl": 3.857633055304177e-05, "clipFraction": 0.0, "explainedVariance": 0.15861013775198962, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 40595, "recentEpisodeCount": 100, "recentReturnMean": 125.80573499896127, "recentReturnMedian": 130.1732822600752, "recentLengthMean": 50.94, "recentLandingRate": 0.98 }, { "update": 619, "trainingStep": 2535424, "elapsedSeconds": 102.5068311659852, "environmentStepsPerSecond": 24734.19547907485, "learningRate": 5.859375e-05, "loss": 23.937422573566437, "policyLoss": -0.000393387716030702, "valueLoss": 47.89362919330597, "entropy": 0.8998364768922329, "approximateKl": 8.62385677464772e-05, "clipFraction": 0.0, "explainedVariance": 0.29099948599476955, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 40674, "recentEpisodeCount": 100, "recentReturnMean": 127.37779577169684, "recentReturnMedian": 129.80647013057023, "recentLengthMean": 50.24, "recentLandingRate": 0.99 }, { "update": 620, "trainingStep": 2539520, "elapsedSeconds": 102.66311245798715, "environmentStepsPerSecond": 24736.44076434219, "learningRate": 5.820312499999999e-05, "loss": 66.32084608078003, "policyLoss": -0.0010334803373552859, "valueLoss": 132.66167068481445, "entropy": 0.8955355435609818, "approximateKl": 0.00017311217743554153, "clipFraction": 0.0, "explainedVariance": 0.12122321347846665, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 40757, "recentEpisodeCount": 100, "recentReturnMean": 120.61115709334496, "recentReturnMedian": 129.5723301046528, "recentLengthMean": 51.13, "recentLandingRate": 0.96 }, { "update": 621, "trainingStep": 2543616, "elapsedSeconds": 102.81645149999531, "environmentStepsPerSecond": 24739.387159263282, "learningRate": 5.781250000000001e-05, "loss": 66.62542963027954, "policyLoss": -3.699181252159178e-05, "valueLoss": 133.2689242362976, "entropy": 0.899629320949316, "approximateKl": 2.659385063452646e-05, "clipFraction": 0.0, "explainedVariance": 0.10332248490078721, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 40831, "recentEpisodeCount": 100, "recentReturnMean": 119.25350540717801, "recentReturnMedian": 130.0021071927622, "recentLengthMean": 51.05, "recentLandingRate": 0.95 }, { "update": 622, "trainingStep": 2547712, "elapsedSeconds": 102.97148424998159, "environmentStepsPerSecond": 24741.917809157498, "learningRate": 5.7421875e-05, "loss": 2.286016523838043, "policyLoss": -0.00019112654263153672, "valueLoss": 4.590661823749542, "entropy": 0.9123289324343204, "approximateKl": 2.1577005099970847e-05, "clipFraction": 0.0, "explainedVariance": 0.8719185341824056, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 40921, "recentEpisodeCount": 100, "recentReturnMean": 129.82426354169453, "recentReturnMedian": 129.7299936604686, "recentLengthMean": 50.15, "recentLandingRate": 1.0 }, { "update": 623, "trainingStep": 2551808, "elapsedSeconds": 103.1272172909812, "environmentStepsPerSecond": 24744.272821789436, "learningRate": 5.703124999999999e-05, "loss": 23.067149758338928, "policyLoss": -0.0002990806242451072, "valueLoss": 46.15310442447662, "entropy": 0.9103586263954639, "approximateKl": 4.3992640712531283e-05, "clipFraction": 0.0, "explainedVariance": 0.31762251199051605, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 40998, "recentEpisodeCount": 100, "recentReturnMean": 127.88445775058295, "recentReturnMedian": 130.09086478641257, "recentLengthMean": 49.99, "recentLandingRate": 0.99 }, { "update": 624, "trainingStep": 2555904, "elapsedSeconds": 103.29284762497991, "environmentStepsPerSecond": 24744.249565851747, "learningRate": 5.6640625e-05, "loss": 2.5349749475717545, "policyLoss": -0.0001262431323993951, "valueLoss": 5.088191717863083, "entropy": 0.8994679264724255, "approximateKl": 5.461001273943111e-05, "clipFraction": 0.0, "explainedVariance": 0.8381079324818015, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 41083, "recentEpisodeCount": 100, "recentReturnMean": 129.45341331937797, "recentReturnMedian": 129.31638155179098, "recentLengthMean": 50.33, "recentLandingRate": 1.0 }, { "update": 625, "trainingStep": 2560000, "elapsedSeconds": 103.46319091599435, "environmentStepsPerSecond": 24743.09923495942, "learningRate": 5.625e-05, "loss": 20.974916726350784, "policyLoss": -0.00028504406509455293, "valueLoss": 41.968637108802795, "entropy": 0.9116900153458118, "approximateKl": 0.0001000427691906225, "clipFraction": 0.0, "explainedVariance": 0.3304516827336209, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 41163, "recentEpisodeCount": 100, "recentReturnMean": 127.41253363352268, "recentReturnMedian": 129.62710576457903, "recentLengthMean": 50.2, "recentLandingRate": 0.99 }, { "update": 626, "trainingStep": 2564096, "elapsedSeconds": 103.6553772079933, "environmentStepsPerSecond": 24736.738884804057, "learningRate": 5.585937499999999e-05, "loss": 22.565654814243317, "policyLoss": -0.0001433308352716267, "valueLoss": 45.14989769458771, "entropy": 0.9150477536022663, "approximateKl": 8.508323298883624e-05, "clipFraction": 0.0, "explainedVariance": 0.33636065626387734, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 41243, "recentEpisodeCount": 100, "recentReturnMean": 127.67745138639876, "recentReturnMedian": 130.01703713904135, "recentLengthMean": 49.56, "recentLandingRate": 0.99 }, { "update": 627, "trainingStep": 2568192, "elapsedSeconds": 103.82044612499885, "environmentStepsPerSecond": 24736.861532148694, "learningRate": 5.546875e-05, "loss": 3.4673570096492767, "policyLoss": -0.0002969050547108054, "valueLoss": 6.953376621007919, "entropy": 0.9034415632486343, "approximateKl": 2.6560031983535737e-05, "clipFraction": 0.0, "explainedVariance": 0.7602191526631416, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 41329, "recentEpisodeCount": 100, "recentReturnMean": 129.4338915332909, "recentReturnMedian": 129.51123340288177, "recentLengthMean": 50.85, "recentLandingRate": 1.0 }, { "update": 628, "trainingStep": 2572288, "elapsedSeconds": 103.97915749999811, "environmentStepsPerSecond": 24738.496270274616, "learningRate": 5.507812499999999e-05, "loss": 19.50326532125473, "policyLoss": -0.00013693346409127116, "valueLoss": 39.02527320384979, "entropy": 0.9234578348696232, "approximateKl": 9.905400656862184e-05, "clipFraction": 0.0, "explainedVariance": 0.3423127370825072, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 41406, "recentEpisodeCount": 100, "recentReturnMean": 127.35314361649172, "recentReturnMedian": 129.39763025473803, "recentLengthMean": 49.94, "recentLandingRate": 0.99 }, { "update": 629, "trainingStep": 2576384, "elapsedSeconds": 104.1382609999855, "environmentStepsPerSecond": 24740.032868422477, "learningRate": 5.468749999999998e-05, "loss": 1.924711525440216, "policyLoss": -5.2498362492769957e-05, "valueLoss": 3.8678191155195236, "entropy": 0.9145516604185104, "approximateKl": 1.9894949218723923e-05, "clipFraction": 0.0, "explainedVariance": 0.8744152183069901, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 41491, "recentEpisodeCount": 100, "recentReturnMean": 129.96162098207844, "recentReturnMedian": 129.8622492174618, "recentLengthMean": 50.2, "recentLandingRate": 1.0 }, { "update": 630, "trainingStep": 2580480, "elapsedSeconds": 104.29390737498761, "environmentStepsPerSecond": 24742.384909618086, "learningRate": 5.4296875000000004e-05, "loss": 2.211086332798004, "policyLoss": -0.00015064782928675413, "valueLoss": 4.440605401992798, "entropy": 0.906568132340908, "approximateKl": 2.8675280191237107e-05, "clipFraction": 0.0, "explainedVariance": 0.841614011499046, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 41569, "recentEpisodeCount": 100, "recentReturnMean": 129.536081473855, "recentReturnMedian": 129.92906193900853, "recentLengthMean": 50.54, "recentLandingRate": 1.0 }, { "update": 631, "trainingStep": 2584576, "elapsedSeconds": 104.44724695797777, "environmentStepsPerSecond": 24745.27644601156, "learningRate": 5.390624999999999e-05, "loss": 44.62188923358917, "policyLoss": -4.705382161773741e-05, "valueLoss": 89.26199460029602, "entropy": 0.906089898198843, "approximateKl": 3.960441972594708e-06, "clipFraction": 0.0, "explainedVariance": 0.1866679331908052, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 41655, "recentEpisodeCount": 100, "recentReturnMean": 125.09349262370147, "recentReturnMedian": 129.2406391958939, "recentLengthMean": 49.46, "recentLandingRate": 0.98 }, { "update": 632, "trainingStep": 2588672, "elapsedSeconds": 104.6019905829744, "environmentStepsPerSecond": 24747.82731736414, "learningRate": 5.351562499999998e-05, "loss": 2.109521195292473, "policyLoss": 1.557127689011395e-05, "valueLoss": 4.237288236618042, "entropy": 0.9138507097959518, "approximateKl": 4.949884896632284e-06, "clipFraction": 0.0, "explainedVariance": 0.857238044753762, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 41733, "recentEpisodeCount": 100, "recentReturnMean": 127.7023071785344, "recentReturnMedian": 130.14189302397426, "recentLengthMean": 50.42, "recentLandingRate": 0.99 }, { "update": 633, "trainingStep": 2592768, "elapsedSeconds": 104.7572239159781, "environmentStepsPerSecond": 24750.25495215073, "learningRate": 5.3125000000000004e-05, "loss": 1.587209478020668, "policyLoss": -0.0006334781646728516, "valueLoss": 3.1939135640859604, "entropy": 0.9113807193934917, "approximateKl": 7.404873758787289e-05, "clipFraction": 0.0, "explainedVariance": 0.8833892051833545, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 41818, "recentEpisodeCount": 100, "recentReturnMean": 129.4492829768594, "recentReturnMedian": 129.45284036372323, "recentLengthMean": 49.72, "recentLandingRate": 1.0 }, { "update": 634, "trainingStep": 2596864, "elapsedSeconds": 104.9107528749737, "environmentStepsPerSecond": 24753.077533384836, "learningRate": 5.273437499999999e-05, "loss": 2.8675470501184464, "policyLoss": -0.0004180305259069428, "valueLoss": 5.753956288099289, "entropy": 0.9013078287243843, "approximateKl": 0.00010638262028805912, "clipFraction": 0.0, "explainedVariance": 0.8042134468031269, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 41899, "recentEpisodeCount": 100, "recentReturnMean": 129.6195823869192, "recentReturnMedian": 129.58099168119952, "recentLengthMean": 50.45, "recentLandingRate": 1.0 }, { "update": 635, "trainingStep": 2600960, "elapsedSeconds": 105.06569420799497, "environmentStepsPerSecond": 24755.55907764687, "learningRate": 5.234374999999998e-05, "loss": 15.465592175722122, "policyLoss": -0.0012520405871327966, "valueLoss": 30.951484978199005, "entropy": 0.8898269422352314, "approximateKl": 0.00023886858252808452, "clipFraction": 6.103515625e-05, "explainedVariance": 0.41515443459374124, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 41980, "recentEpisodeCount": 100, "recentReturnMean": 127.40760565616009, "recentReturnMedian": 129.66225095372647, "recentLengthMean": 50.7, "recentLandingRate": 0.99 }, { "update": 636, "trainingStep": 2605056, "elapsedSeconds": 105.21785791599541, "environmentStepsPerSecond": 24758.686895905477, "learningRate": 5.1953125000000004e-05, "loss": 2.610122397542, "policyLoss": 0.00013667531311511993, "valueLoss": 5.238263249397278, "entropy": 0.9145909734070301, "approximateKl": 0.00014796301184105687, "clipFraction": 0.0, "explainedVariance": 0.818933626634266, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 42063, "recentEpisodeCount": 100, "recentReturnMean": 129.58566553847405, "recentReturnMedian": 129.62529340852052, "recentLengthMean": 50.63, "recentLandingRate": 1.0 }, { "update": 637, "trainingStep": 2609152, "elapsedSeconds": 105.37074245797703, "environmentStepsPerSecond": 24761.63628666238, "learningRate": 5.156249999999999e-05, "loss": 22.348820239305496, "policyLoss": -0.00011339772026985884, "valueLoss": 44.71625244617462, "entropy": 0.919254757463932, "approximateKl": 5.912041160627268e-05, "clipFraction": 0.0, "explainedVariance": 0.2929868780502296, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 42141, "recentEpisodeCount": 100, "recentReturnMean": 127.48065572766762, "recentReturnMedian": 129.9093262529932, "recentLengthMean": 50.41, "recentLandingRate": 0.99 }, { "update": 638, "trainingStep": 2613248, "elapsedSeconds": 105.52946612497908, "environmentStepsPerSecond": 24763.206864944405, "learningRate": 5.117187499999998e-05, "loss": 1.9294044375419617, "policyLoss": -0.0002173320099245757, "valueLoss": 3.8772540986537933, "entropy": 0.9005278311669827, "approximateKl": 5.328803672455251e-05, "clipFraction": 0.0, "explainedVariance": 0.8631947686887993, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 42222, "recentEpisodeCount": 100, "recentReturnMean": 129.79803782980306, "recentReturnMedian": 129.8035883596167, "recentLengthMean": 50.89, "recentLandingRate": 1.0 }, { "update": 639, "trainingStep": 2617344, "elapsedSeconds": 105.68428575000144, "environmentStepsPerSecond": 24765.68755161374, "learningRate": 5.0781250000000004e-05, "loss": 2.331189677119255, "policyLoss": -0.00021868915064260364, "valueLoss": 4.681123852729797, "entropy": 0.9153554700314999, "approximateKl": 4.211868144921027e-05, "clipFraction": 0.0, "explainedVariance": 0.8326144332090188, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 42306, "recentEpisodeCount": 100, "recentReturnMean": 129.51251353258382, "recentReturnMedian": 129.51162380562164, "recentLengthMean": 50.45, "recentLandingRate": 1.0 }, { "update": 640, "trainingStep": 2621440, "elapsedSeconds": 105.83632458298234, "environmentStepsPerSecond": 24768.81175087128, "learningRate": 5.039062499999999e-05, "loss": 39.16421812772751, "policyLoss": -0.0007805035565979779, "valueLoss": 78.34817624092102, "entropy": 0.9089442491531372, "approximateKl": 0.00011980058116023429, "clipFraction": 0.0, "explainedVariance": 0.18047944249778924, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 42385, "recentEpisodeCount": 100, "recentReturnMean": 125.24092296932388, "recentReturnMedian": 129.7855342834955, "recentLengthMean": 49.71, "recentLandingRate": 0.98 }, { "update": 641, "trainingStep": 2625536, "elapsedSeconds": 105.99350479099667, "environmentStepsPerSecond": 24770.725387156166, "learningRate": 4.999999999999998e-05, "loss": 23.57850193977356, "policyLoss": -0.00012611653073690832, "valueLoss": 47.17529630661011, "entropy": 0.901987262070179, "approximateKl": 0.00010459013719810173, "clipFraction": 0.0, "explainedVariance": 0.31198292831018515, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 42472, "recentEpisodeCount": 100, "recentReturnMean": 127.70381787234743, "recentReturnMedian": 129.62444049026817, "recentLengthMean": 49.85, "recentLandingRate": 0.99 }, { "update": 642, "trainingStep": 2629632, "elapsedSeconds": 106.14969620798365, "environmentStepsPerSecond": 24772.864114916065, "learningRate": 4.9609375000000005e-05, "loss": 23.643032610416412, "policyLoss": -0.0005283196223899722, "valueLoss": 47.30494678020477, "entropy": 0.8912578299641609, "approximateKl": 8.336836981470697e-05, "clipFraction": 0.0, "explainedVariance": 0.2811072528153915, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 42543, "recentEpisodeCount": 100, "recentReturnMean": 127.74966448343301, "recentReturnMedian": 130.11209804806276, "recentLengthMean": 50.23, "recentLandingRate": 0.99 }, { "update": 643, "trainingStep": 2633728, "elapsedSeconds": 106.31066983297933, "environmentStepsPerSecond": 24773.882096103338, "learningRate": 4.9218749999999994e-05, "loss": 23.07893595099449, "policyLoss": -0.000430845218943432, "valueLoss": 46.17681264877319, "entropy": 0.9039446637034416, "approximateKl": 0.00019033056014450267, "clipFraction": 0.0, "explainedVariance": 0.3335764268349678, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 42633, "recentEpisodeCount": 100, "recentReturnMean": 127.26263275475307, "recentReturnMedian": 129.2488944788929, "recentLengthMean": 49.94, "recentLandingRate": 0.99 }, { "update": 644, "trainingStep": 2637824, "elapsedSeconds": 106.47223549999762, "environmentStepsPerSecond": 24774.75923758602, "learningRate": 4.882812499999998e-05, "loss": 17.748540326952934, "policyLoss": -6.114336429163814e-05, "valueLoss": 35.51555015146732, "entropy": 0.9173617362976074, "approximateKl": 2.2861873731017113e-05, "clipFraction": 0.0, "explainedVariance": 0.36735871187654445, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 42713, "recentEpisodeCount": 100, "recentReturnMean": 127.28050416869449, "recentReturnMedian": 129.694949929195, "recentLengthMean": 49.35, "recentLandingRate": 0.99 }, { "update": 645, "trainingStep": 2641920, "elapsedSeconds": 106.64338812499773, "environmentStepsPerSecond": 24773.40645726091, "learningRate": 4.8437500000000005e-05, "loss": 22.070220232009888, "policyLoss": 4.6252505853772163e-05, "valueLoss": 44.15856087207794, "entropy": 0.910647738724947, "approximateKl": 5.6384436902590096e-05, "clipFraction": 0.0, "explainedVariance": 0.3272622103801349, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 42796, "recentEpisodeCount": 100, "recentReturnMean": 127.26302085032414, "recentReturnMedian": 129.72106342349434, "recentLengthMean": 49.54, "recentLandingRate": 0.99 }, { "update": 646, "trainingStep": 2646016, "elapsedSeconds": 106.8173436249781, "environmentStepsPerSecond": 24771.407996156697, "learningRate": 4.8046874999999994e-05, "loss": 45.375505685806274, "policyLoss": 1.861754572018981e-05, "valueLoss": 90.76916646957397, "entropy": 0.9096468053758144, "approximateKl": 6.136141018941998e-05, "clipFraction": 0.0, "explainedVariance": 0.17864878082377633, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 42881, "recentEpisodeCount": 100, "recentReturnMean": 125.4623501782629, "recentReturnMedian": 130.04195225867443, "recentLengthMean": 49.42, "recentLandingRate": 0.98 }, { "update": 647, "trainingStep": 2650112, "elapsedSeconds": 106.97708341598627, "environmentStepsPerSecond": 24772.707531153133, "learningRate": 4.765624999999998e-05, "loss": 44.059367179870605, "policyLoss": -0.0002334719756618142, "valueLoss": 88.13754653930664, "entropy": 0.9172424301505089, "approximateKl": 2.0414583559613675e-05, "clipFraction": 0.0, "explainedVariance": 0.14900723608324273, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 42957, "recentEpisodeCount": 100, "recentReturnMean": 123.49329008559347, "recentReturnMedian": 129.96584066265495, "recentLengthMean": 50.66, "recentLandingRate": 0.97 }, { "update": 648, "trainingStep": 2654208, "elapsedSeconds": 107.16986016597366, "environmentStepsPerSecond": 24766.366176921718, "learningRate": 4.7265625000000005e-05, "loss": 37.77682685852051, "policyLoss": -0.00014808951527811587, "valueLoss": 75.57220005989075, "entropy": 0.9125387109816074, "approximateKl": 3.1875359127298e-05, "clipFraction": 0.0, "explainedVariance": 0.20595542336394346, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 43039, "recentEpisodeCount": 100, "recentReturnMean": 124.86946845961356, "recentReturnMedian": 129.4803343033418, "recentLengthMean": 51.79, "recentLandingRate": 0.98 }, { "update": 649, "trainingStep": 2658304, "elapsedSeconds": 107.3294317079999, "environmentStepsPerSecond": 24767.707773131355, "learningRate": 4.6874999999999994e-05, "loss": 24.236597269773483, "policyLoss": -0.000383224047254771, "valueLoss": 48.49196672439575, "entropy": 0.900298748165369, "approximateKl": 9.247786874766462e-05, "clipFraction": 0.0, "explainedVariance": 0.28179589685502715, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 43117, "recentEpisodeCount": 100, "recentReturnMean": 126.90906118687272, "recentReturnMedian": 128.96011537010781, "recentLengthMean": 51.32, "recentLandingRate": 0.99 }, { "update": 650, "trainingStep": 2662400, "elapsedSeconds": 107.50225537497317, "environmentStepsPerSecond": 24765.9920316408, "learningRate": 4.648437499999998e-05, "loss": 1.7853414192795753, "policyLoss": 1.6475532902404666e-05, "valueLoss": 3.588879182934761, "entropy": 0.9114640019834042, "approximateKl": 3.102773189311847e-05, "clipFraction": 0.0, "explainedVariance": 0.8801395717061561, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 43200, "recentEpisodeCount": 100, "recentReturnMean": 127.24418145486067, "recentReturnMedian": 129.5364628508687, "recentLengthMean": 49.62, "recentLandingRate": 0.99 }, { "update": 651, "trainingStep": 2666496, "elapsedSeconds": 107.66865895799128, "environmentStepsPerSecond": 24765.758446386684, "learningRate": 4.6093750000000006e-05, "loss": 2.5830900073051453, "policyLoss": -0.00038021811633370817, "valueLoss": 5.1852196753025055, "entropy": 0.9139645472168922, "approximateKl": 4.6597040636697784e-05, "clipFraction": 0.0, "explainedVariance": 0.8122836178885472, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 43282, "recentEpisodeCount": 100, "recentReturnMean": 129.18111588465896, "recentReturnMedian": 129.55063950526528, "recentLengthMean": 50.67, "recentLandingRate": 1.0 }, { "update": 652, "trainingStep": 2670592, "elapsedSeconds": 107.8288106659893, "environmentStepsPerSecond": 24766.961478156616, "learningRate": 4.5703124999999995e-05, "loss": 4.483190029859543, "policyLoss": -0.000669293396640569, "valueLoss": 8.98574486374855, "entropy": 0.9013046436011791, "approximateKl": 5.426121788332239e-05, "clipFraction": 0.00018310546875, "explainedVariance": 0.6756938245108898, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 43353, "recentEpisodeCount": 100, "recentReturnMean": 129.31912015832438, "recentReturnMedian": 129.09551895176992, "recentLengthMean": 50.29, "recentLandingRate": 1.0 }, { "update": 653, "trainingStep": 2674688, "elapsedSeconds": 107.99588554099319, "environmentStepsPerSecond": 24766.573157870345, "learningRate": 4.531249999999998e-05, "loss": 2.2011909186840057, "policyLoss": 0.00030276173492893577, "valueLoss": 4.419952005147934, "entropy": 0.9087866023182869, "approximateKl": 5.221854007686488e-05, "clipFraction": 0.0, "explainedVariance": 0.8480825885075522, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 43442, "recentEpisodeCount": 100, "recentReturnMean": 129.24668245511558, "recentReturnMedian": 129.30913268169388, "recentLengthMean": 52.72, "recentLandingRate": 1.0 }, { "update": 654, "trainingStep": 2678784, "elapsedSeconds": 108.16205779099255, "environmentStepsPerSecond": 24766.392713943744, "learningRate": 4.4921875000000006e-05, "loss": 18.11175549030304, "policyLoss": -0.0008831585000734776, "valueLoss": 36.24360740184784, "entropy": 0.9165053181350231, "approximateKl": 0.0002185854064009618, "clipFraction": 6.103515625e-05, "explainedVariance": 0.35718888680809135, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 43520, "recentEpisodeCount": 100, "recentReturnMean": 127.262689527392, "recentReturnMedian": 129.63671260792762, "recentLengthMean": 49.47, "recentLandingRate": 0.99 }, { "update": 655, "trainingStep": 2682880, "elapsedSeconds": 108.32931924998411, "environmentStepsPerSecond": 24765.963809011875, "learningRate": 4.4531249999999995e-05, "loss": 3.481086805462837, "policyLoss": -0.00011380125943105668, "valueLoss": 6.98032546043396, "entropy": 0.8962071388959885, "approximateKl": 5.070186671218835e-05, "clipFraction": 0.0, "explainedVariance": 0.7632482066120461, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 43602, "recentEpisodeCount": 100, "recentReturnMean": 129.6723832258802, "recentReturnMedian": 129.78172850667033, "recentLengthMean": 51.13, "recentLandingRate": 1.0 }, { "update": 656, "trainingStep": 2686976, "elapsedSeconds": 108.51478012499865, "environmentStepsPerSecond": 24761.38270662172, "learningRate": 4.4140624999999984e-05, "loss": 23.671051681041718, "policyLoss": -0.00016863172641023993, "valueLoss": 47.360555768013, "entropy": 0.9057489596307278, "approximateKl": 2.4218050384661183e-05, "clipFraction": 0.0, "explainedVariance": 0.31845663311379646, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 43685, "recentEpisodeCount": 100, "recentReturnMean": 127.53711632185586, "recentReturnMedian": 129.64550480712205, "recentLengthMean": 49.44, "recentLandingRate": 0.99 }, { "update": 657, "trainingStep": 2691072, "elapsedSeconds": 108.69501595798647, "environmentStepsPerSecond": 24758.00731323478, "learningRate": 4.3750000000000006e-05, "loss": 22.709899365901947, "policyLoss": -0.0003901143791154027, "valueLoss": 45.43854117393494, "entropy": 0.898150198161602, "approximateKl": 4.7093195462366566e-05, "clipFraction": 0.0, "explainedVariance": 0.31233190864489946, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 43766, "recentEpisodeCount": 100, "recentReturnMean": 125.32524091827669, "recentReturnMedian": 129.61061180802062, "recentLengthMean": 50.42, "recentLandingRate": 0.98 }, { "update": 658, "trainingStep": 2695168, "elapsedSeconds": 108.8659981660021, "environmentStepsPerSecond": 24756.747243435253, "learningRate": 4.3359374999999995e-05, "loss": 2.2711694091558456, "policyLoss": 0.00010910455603152514, "valueLoss": 4.560296416282654, "entropy": 0.9087880551815033, "approximateKl": 2.054292053799145e-05, "clipFraction": 0.0, "explainedVariance": 0.8505319791263518, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 43852, "recentEpisodeCount": 100, "recentReturnMean": 129.53716741778655, "recentReturnMedian": 129.54949367139488, "recentLengthMean": 50.0, "recentLandingRate": 1.0 }, { "update": 659, "trainingStep": 2699264, "elapsedSeconds": 109.06682220799848, "environmentStepsPerSecond": 24748.71776178006, "learningRate": 4.2968749999999984e-05, "loss": 2.070554919540882, "policyLoss": -0.00011777906911447644, "valueLoss": 4.1593083292245865, "entropy": 0.8981468267738819, "approximateKl": 1.2494980182964355e-05, "clipFraction": 0.0, "explainedVariance": 0.857600946460758, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 43930, "recentEpisodeCount": 100, "recentReturnMean": 129.5428721058613, "recentReturnMedian": 129.49865570862312, "recentLengthMean": 49.47, "recentLandingRate": 1.0 }, { "update": 660, "trainingStep": 2703360, "elapsedSeconds": 109.39095420797821, "environmentStepsPerSecond": 24712.829498317293, "learningRate": 4.257812500000001e-05, "loss": 37.788214683532715, "policyLoss": -0.0004818312590941787, "valueLoss": 75.59536552429199, "entropy": 0.8986312039196491, "approximateKl": 3.0732149753021076e-05, "clipFraction": 0.0, "explainedVariance": 0.21699293029933464, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 44013, "recentEpisodeCount": 100, "recentReturnMean": 125.47114430346599, "recentReturnMedian": 129.94574866545736, "recentLengthMean": 50.79, "recentLandingRate": 0.98 }, { "update": 661, "trainingStep": 2707456, "elapsedSeconds": 109.82713945797877, "environmentStepsPerSecond": 24651.97594476096, "learningRate": 4.2187499999999995e-05, "loss": 1.601727306842804, "policyLoss": 8.373259333893657e-05, "valueLoss": 3.221425488591194, "entropy": 0.9069173708558083, "approximateKl": 1.2876640539616346e-05, "clipFraction": 0.0, "explainedVariance": 0.8965354541880718, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 44096, "recentEpisodeCount": 100, "recentReturnMean": 127.41571328462858, "recentReturnMedian": 129.34203832026105, "recentLengthMean": 49.33, "recentLandingRate": 0.99 }, { "update": 662, "trainingStep": 2711552, "elapsedSeconds": 110.16013774997555, "environmentStepsPerSecond": 24614.638792067068, "learningRate": 4.1796874999999984e-05, "loss": 3.26067191362381, "policyLoss": -0.00032116094371303916, "valueLoss": 6.540053188800812, "entropy": 0.903351116925478, "approximateKl": 3.2284155167872086e-05, "clipFraction": 0.0, "explainedVariance": 0.7660027835877777, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 44176, "recentEpisodeCount": 100, "recentReturnMean": 130.0379243424572, "recentReturnMedian": 130.06213703379035, "recentLengthMean": 50.98, "recentLandingRate": 1.0 }, { "update": 663, "trainingStep": 2715648, "elapsedSeconds": 110.40772654098691, "environmentStepsPerSecond": 24596.53943686508, "learningRate": 4.140625000000001e-05, "loss": 41.64424467086792, "policyLoss": -0.00031760561978444457, "valueLoss": 83.3070740699768, "entropy": 0.8974809609353542, "approximateKl": 8.418007564614527e-05, "clipFraction": 0.0, "explainedVariance": 0.19578752252218712, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 44260, "recentEpisodeCount": 100, "recentReturnMean": 125.4502902275027, "recentReturnMedian": 129.51766271539964, "recentLengthMean": 50.27, "recentLandingRate": 0.98 }, { "update": 664, "trainingStep": 2719744, "elapsedSeconds": 110.59481124999002, "environmentStepsPerSecond": 24591.967464479447, "learningRate": 4.1015624999999996e-05, "loss": 15.900176540017128, "policyLoss": -8.546750177629292e-05, "valueLoss": 31.81854073703289, "entropy": 0.9008557088673115, "approximateKl": 4.7941270167939365e-05, "clipFraction": 0.0, "explainedVariance": 0.4215851836621186, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 44340, "recentEpisodeCount": 100, "recentReturnMean": 127.07863903912366, "recentReturnMedian": 128.94525503134355, "recentLengthMean": 49.33, "recentLandingRate": 0.99 }, { "update": 665, "trainingStep": 2723840, "elapsedSeconds": 110.76937866598018, "environmentStepsPerSecond": 24590.189389918043, "learningRate": 4.0624999999999985e-05, "loss": 60.577388048172, "policyLoss": -4.006952804047614e-05, "valueLoss": 121.17274856567383, "entropy": 0.894679568707943, "approximateKl": 1.766732384567149e-05, "clipFraction": 0.0, "explainedVariance": 0.11643849384940175, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 44421, "recentEpisodeCount": 100, "recentReturnMean": 123.06106729929219, "recentReturnMedian": 129.51123647356872, "recentLengthMean": 50.13, "recentLandingRate": 0.97 }, { "update": 666, "trainingStep": 2727936, "elapsedSeconds": 110.94151041598525, "environmentStepsPerSecond": 24588.95673739574, "learningRate": 4.023437500000001e-05, "loss": 2.104989416897297, "policyLoss": -0.00024393874628003687, "valueLoss": 4.228649139404297, "entropy": 0.9091144315898418, "approximateKl": 1.534849070594646e-05, "clipFraction": 0.0, "explainedVariance": 0.8627658184000506, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 44506, "recentEpisodeCount": 100, "recentReturnMean": 125.13699436091557, "recentReturnMedian": 129.37685045896797, "recentLengthMean": 49.51, "recentLandingRate": 0.98 }, { "update": 667, "trainingStep": 2732032, "elapsedSeconds": 111.1218909159943, "environmentStepsPerSecond": 24585.90271889232, "learningRate": 3.9843749999999996e-05, "loss": 24.27345037460327, "policyLoss": -0.00011008139699697495, "valueLoss": 48.56513983011246, "entropy": 0.9009764343500137, "approximateKl": 4.83412659377791e-05, "clipFraction": 0.0, "explainedVariance": 0.29185790169386494, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 44584, "recentEpisodeCount": 100, "recentReturnMean": 127.54725160962661, "recentReturnMedian": 129.48801497742534, "recentLengthMean": 50.62, "recentLandingRate": 0.99 }, { "update": 668, "trainingStep": 2736128, "elapsedSeconds": 111.29411591598182, "environmentStepsPerSecond": 24584.660001841952, "learningRate": 3.9453124999999985e-05, "loss": 23.452368438243866, "policyLoss": -4.452053690329194e-05, "valueLoss": 46.92266261577606, "entropy": 0.89185581356287, "approximateKl": 1.3953969755675644e-05, "clipFraction": 0.0, "explainedVariance": 0.31726970433778545, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 44668, "recentEpisodeCount": 100, "recentReturnMean": 127.74322869169443, "recentReturnMedian": 130.01927205658467, "recentLengthMean": 51.34, "recentLandingRate": 0.99 }, { "update": 669, "trainingStep": 2740224, "elapsedSeconds": 111.45354462499381, "environmentStepsPerSecond": 24586.243615849038, "learningRate": 3.906250000000001e-05, "loss": 43.26258099079132, "policyLoss": -0.00021364996791817248, "valueLoss": 86.5435676574707, "entropy": 0.8989083096385002, "approximateKl": 3.254037073929794e-05, "clipFraction": 0.0, "explainedVariance": 0.19917290418791223, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 44751, "recentEpisodeCount": 100, "recentReturnMean": 124.8001050778132, "recentReturnMedian": 128.74049957096577, "recentLengthMean": 49.26, "recentLandingRate": 0.98 }, { "update": 670, "trainingStep": 2744320, "elapsedSeconds": 111.60952829098096, "environmentStepsPerSecond": 24588.581656264963, "learningRate": 3.8671874999999996e-05, "loss": 2.025133863091469, "policyLoss": 2.565476461313665e-05, "valueLoss": 4.068288877606392, "entropy": 0.9036246463656425, "approximateKl": 1.3535071047954261e-05, "clipFraction": 0.0, "explainedVariance": 0.8768916210891244, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 44833, "recentEpisodeCount": 100, "recentReturnMean": 127.61057150745656, "recentReturnMedian": 129.91160184470937, "recentLengthMean": 49.76, "recentLandingRate": 0.99 }, { "update": 671, "trainingStep": 2748416, "elapsedSeconds": 111.77248820799286, "environmentStepsPerSecond": 24589.378335083537, "learningRate": 3.8281249999999985e-05, "loss": 64.7314190864563, "policyLoss": -1.9276660168543458e-05, "valueLoss": 129.4808793067932, "entropy": 0.9000642225146294, "approximateKl": 1.0333133104722947e-06, "clipFraction": 0.0, "explainedVariance": 0.1301877254428121, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 44914, "recentEpisodeCount": 100, "recentReturnMean": 123.27397732838836, "recentReturnMedian": 129.38420981675154, "recentLengthMean": 50.21, "recentLandingRate": 0.97 }, { "update": 672, "trainingStep": 2752512, "elapsedSeconds": 111.94486624997808, "environmentStepsPerSecond": 24588.103878328042, "learningRate": 3.789062500000001e-05, "loss": 22.75985062122345, "policyLoss": -0.0003855905815726146, "valueLoss": 45.53861975669861, "entropy": 0.9073767587542534, "approximateKl": 3.108717646682635e-05, "clipFraction": 0.0, "explainedVariance": 0.3298246705931335, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 44996, "recentEpisodeCount": 100, "recentReturnMean": 122.92521568516277, "recentReturnMedian": 129.40331863658503, "recentLengthMean": 49.21, "recentLandingRate": 0.97 }, { "update": 673, "trainingStep": 2756608, "elapsedSeconds": 112.09898949999479, "environmentStepsPerSecond": 24590.837190375638, "learningRate": 3.75e-05, "loss": 1.7645212933421135, "policyLoss": -0.00010718603152781725, "valueLoss": 3.5471224188804626, "entropy": 0.8932705111801624, "approximateKl": 2.9290175007190555e-05, "clipFraction": 0.0, "explainedVariance": 0.8815969375532482, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 45079, "recentEpisodeCount": 100, "recentReturnMean": 127.054076087047, "recentReturnMedian": 129.13036768178426, "recentLengthMean": 49.86, "recentLandingRate": 0.99 }, { "update": 674, "trainingStep": 2760704, "elapsedSeconds": 112.25955616598367, "environmentStepsPerSecond": 24592.151388146453, "learningRate": 3.7109374999999986e-05, "loss": 2.9545684158802032, "policyLoss": -8.870917372405529e-05, "valueLoss": 5.927393674850464, "entropy": 0.9039729833602905, "approximateKl": 3.1920571927912533e-06, "clipFraction": 0.0, "explainedVariance": 0.7859384266182559, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 45159, "recentEpisodeCount": 100, "recentReturnMean": 130.09834009738537, "recentReturnMedian": 130.158758472302, "recentLengthMean": 50.87, "recentLandingRate": 1.0 }, { "update": 675, "trainingStep": 2764800, "elapsedSeconds": 112.4232632079802, "environmentStepsPerSecond": 24592.774850212183, "learningRate": 3.671875000000001e-05, "loss": 2.8416579216718674, "policyLoss": -0.00031981803476810455, "valueLoss": 5.701912432909012, "entropy": 0.8978447988629341, "approximateKl": 3.2907253626035526e-05, "clipFraction": 0.0, "explainedVariance": 0.8018995380581685, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 45242, "recentEpisodeCount": 100, "recentReturnMean": 129.78111780554042, "recentReturnMedian": 129.91937656314985, "recentLengthMean": 51.41, "recentLandingRate": 1.0 }, { "update": 676, "trainingStep": 2768896, "elapsedSeconds": 112.5785397499858, "environmentStepsPerSecond": 24595.238187927815, "learningRate": 3.6328125e-05, "loss": 1.6571051478385925, "policyLoss": -0.0001075488980859518, "valueLoss": 3.3325737565755844, "entropy": 0.907416183501482, "approximateKl": 3.9470643969252706e-05, "clipFraction": 0.0, "explainedVariance": 0.8926975382153399, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 45325, "recentEpisodeCount": 100, "recentReturnMean": 128.96599736093356, "recentReturnMedian": 128.97665190161206, "recentLengthMean": 48.61, "recentLandingRate": 1.0 }, { "update": 677, "trainingStep": 2772992, "elapsedSeconds": 112.73308224999346, "environmentStepsPerSecond": 24597.85490341422, "learningRate": 3.5937499999999986e-05, "loss": 2.2257183343172073, "policyLoss": -0.00026106153381988406, "valueLoss": 4.4700131714344025, "entropy": 0.9027182199060917, "approximateKl": 2.6753008569357917e-05, "clipFraction": 0.0, "explainedVariance": 0.8496032482345734, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 45407, "recentEpisodeCount": 100, "recentReturnMean": 129.5637638449091, "recentReturnMedian": 129.51561212865636, "recentLengthMean": 49.62, "recentLandingRate": 1.0 }, { "update": 678, "trainingStep": 2777088, "elapsedSeconds": 112.89114162497572, "environmentStepsPerSecond": 24599.698081054794, "learningRate": 3.554687500000001e-05, "loss": 1.7011366933584213, "policyLoss": -0.0003852995578199625, "valueLoss": 3.4212214946746826, "entropy": 0.9088749587535858, "approximateKl": 3.628303966252133e-05, "clipFraction": 0.0, "explainedVariance": 0.8938871048815197, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 45491, "recentEpisodeCount": 100, "recentReturnMean": 129.41949373280715, "recentReturnMedian": 129.30637083295733, "recentLengthMean": 48.93, "recentLandingRate": 1.0 }, { "update": 679, "trainingStep": 2781184, "elapsedSeconds": 113.04446449998068, "environmentStepsPerSecond": 24602.56689526337, "learningRate": 3.515625e-05, "loss": 35.29166376590729, "policyLoss": -0.00018090882804244757, "valueLoss": 70.60156035423279, "entropy": 0.8935615606606007, "approximateKl": 1.648887700866908e-05, "clipFraction": 0.0, "explainedVariance": 0.23382877027557203, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 45576, "recentEpisodeCount": 100, "recentReturnMean": 125.26091125574482, "recentReturnMedian": 129.41001573880203, "recentLengthMean": 49.1, "recentLandingRate": 0.98 }, { "update": 680, "trainingStep": 2785280, "elapsedSeconds": 113.20218170798034, "environmentStepsPerSecond": 24604.4727935102, "learningRate": 3.4765624999999986e-05, "loss": 22.24838411808014, "policyLoss": -0.00018757488578557968, "valueLoss": 44.51516395807266, "entropy": 0.901030957698822, "approximateKl": 1.2734315532725304e-05, "clipFraction": 0.0, "explainedVariance": 0.3433295512361605, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 45659, "recentEpisodeCount": 100, "recentReturnMean": 127.0244164925834, "recentReturnMedian": 129.36698230961338, "recentLengthMean": 48.8, "recentLandingRate": 0.99 }, { "update": 681, "trainingStep": 2789376, "elapsedSeconds": 113.3641927499848, "environmentStepsPerSecond": 24605.441386167982, "learningRate": 3.437500000000001e-05, "loss": 44.537848353385925, "policyLoss": -4.1504710679873824e-05, "valueLoss": 89.09379410743713, "entropy": 0.9006595611572266, "approximateKl": 5.08927769260481e-06, "clipFraction": 0.0, "explainedVariance": 0.19324621609757953, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 45741, "recentEpisodeCount": 100, "recentReturnMean": 125.48809594654274, "recentReturnMedian": 130.12092292768648, "recentLengthMean": 49.59, "recentLandingRate": 0.98 }, { "update": 682, "trainingStep": 2793472, "elapsedSeconds": 113.52276187497773, "environmentStepsPerSecond": 24607.15326038704, "learningRate": 3.3984375e-05, "loss": 2.1227466613054276, "policyLoss": -8.608630741946399e-05, "valueLoss": 4.263547405600548, "entropy": 0.8940947167575359, "approximateKl": 8.133596566040069e-06, "clipFraction": 0.0, "explainedVariance": 0.8392811265826896, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 45820, "recentEpisodeCount": 100, "recentReturnMean": 130.0388930985226, "recentReturnMedian": 130.5410417295061, "recentLengthMean": 50.97, "recentLandingRate": 1.0 }, { "update": 683, "trainingStep": 2797568, "elapsedSeconds": 113.68376658298075, "environmentStepsPerSecond": 24608.3331339834, "learningRate": 3.3593749999999986e-05, "loss": 23.370018124580383, "policyLoss": -6.228231359273195e-05, "valueLoss": 46.75814414024353, "entropy": 0.899154644459486, "approximateKl": 9.231429430656135e-06, "clipFraction": 0.0, "explainedVariance": 0.3415967912259722, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 45908, "recentEpisodeCount": 100, "recentReturnMean": 127.48026243842907, "recentReturnMedian": 129.65176358103054, "recentLengthMean": 48.92, "recentLandingRate": 0.99 }, { "update": 684, "trainingStep": 2801664, "elapsedSeconds": 113.84068529098295, "environmentStepsPerSecond": 24610.392961345897, "learningRate": 3.320312500000001e-05, "loss": 1.4612090364098549, "policyLoss": -4.665454616770148e-05, "valueLoss": 2.9406125843524933, "entropy": 0.9050606898963451, "approximateKl": 2.7418063837103546e-06, "clipFraction": 0.0, "explainedVariance": 0.890754559302662, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 45986, "recentEpisodeCount": 100, "recentReturnMean": 129.47530790083619, "recentReturnMedian": 129.56053115520626, "recentLengthMean": 49.12, "recentLandingRate": 1.0 }, { "update": 685, "trainingStep": 2805760, "elapsedSeconds": 113.99357487499947, "environmentStepsPerSecond": 24613.31704946246, "learningRate": 3.28125e-05, "loss": 2.257948338985443, "policyLoss": -0.00032777865999378264, "valueLoss": 4.5347315818071365, "entropy": 0.9089674204587936, "approximateKl": 6.207730621099472e-06, "clipFraction": 0.0, "explainedVariance": 0.8374801730307715, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 46070, "recentEpisodeCount": 100, "recentReturnMean": 129.29048540905612, "recentReturnMedian": 129.32077785138972, "recentLengthMean": 50.09, "recentLandingRate": 1.0 }, { "update": 686, "trainingStep": 2809856, "elapsedSeconds": 114.1514973329904, "environmentStepsPerSecond": 24615.147988846715, "learningRate": 3.242187499999999e-05, "loss": 83.03439617156982, "policyLoss": -0.00013066275278106332, "valueLoss": 166.087016582489, "entropy": 0.898105014115572, "approximateKl": 1.6015263099689037e-05, "clipFraction": 0.0, "explainedVariance": 0.07823714083152344, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 46152, "recentEpisodeCount": 100, "recentReturnMean": 120.72209608115838, "recentReturnMedian": 129.38149826577865, "recentLengthMean": 50.29, "recentLandingRate": 0.96 }, { "update": 687, "trainingStep": 2813952, "elapsedSeconds": 114.31134670798201, "environmentStepsPerSecond": 24616.55890721398, "learningRate": 3.203125000000001e-05, "loss": 36.353198885917664, "policyLoss": -0.00011580655700527132, "valueLoss": 72.72449159622192, "entropy": 0.8931257575750351, "approximateKl": 2.8383288736222312e-05, "clipFraction": 0.0, "explainedVariance": 0.212921888377532, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 46231, "recentEpisodeCount": 100, "recentReturnMean": 123.00010944643, "recentReturnMedian": 129.427415436483, "recentLengthMean": 50.92, "recentLandingRate": 0.97 }, { "update": 688, "trainingStep": 2818048, "elapsedSeconds": 114.46888470798149, "environmentStepsPerSecond": 24618.462975235994, "learningRate": 3.1640625e-05, "loss": 65.69670760631561, "policyLoss": -5.921826232224703e-05, "valueLoss": 131.4114694595337, "entropy": 0.8968625776469707, "approximateKl": 1.034186061588116e-05, "clipFraction": 0.0, "explainedVariance": 0.10883020165993129, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 46315, "recentEpisodeCount": 100, "recentReturnMean": 123.0670448917734, "recentReturnMedian": 129.45466705165018, "recentLengthMean": 49.88, "recentLandingRate": 0.97 }, { "update": 689, "trainingStep": 2822144, "elapsedSeconds": 114.6270549579931, "environmentStepsPerSecond": 24620.226010641374, "learningRate": 3.124999999999999e-05, "loss": 63.93287515640259, "policyLoss": -0.0002774768800009042, "valueLoss": 127.8841700553894, "entropy": 0.8932504318654537, "approximateKl": 1.0384417691966519e-05, "clipFraction": 0.0, "explainedVariance": 0.12760964681629816, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 46398, "recentEpisodeCount": 100, "recentReturnMean": 123.45411790950067, "recentReturnMedian": 129.93523959768936, "recentLengthMean": 49.54, "recentLandingRate": 0.97 }, { "update": 690, "trainingStep": 2826240, "elapsedSeconds": 114.78844999999274, "environmentStepsPerSecond": 24621.29247324255, "learningRate": 3.085937500000001e-05, "loss": 22.86574250459671, "policyLoss": -0.0001314583932980895, "valueLoss": 45.74968361854553, "entropy": 0.8967840299010277, "approximateKl": 2.1946238121017814e-05, "clipFraction": 0.0, "explainedVariance": 0.34388929390394896, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 46479, "recentEpisodeCount": 100, "recentReturnMean": 125.6393705087772, "recentReturnMedian": 129.89347947295755, "recentLengthMean": 50.0, "recentLandingRate": 0.98 }, { "update": 691, "trainingStep": 2830336, "elapsedSeconds": 114.94908054097323, "environmentStepsPerSecond": 24622.51969898216, "learningRate": 3.046875e-05, "loss": 44.72750163078308, "policyLoss": -0.00019972448353655636, "valueLoss": 89.47327780723572, "entropy": 0.8937173746526241, "approximateKl": 1.7083497368730605e-05, "clipFraction": 0.0, "explainedVariance": 0.18006991873950706, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 46560, "recentEpisodeCount": 100, "recentReturnMean": 125.3734629554639, "recentReturnMedian": 129.59152431646362, "recentLengthMean": 50.48, "recentLandingRate": 0.98 }, { "update": 692, "trainingStep": 2834432, "elapsedSeconds": 115.17119554098463, "environmentStepsPerSecond": 24610.598046551873, "learningRate": 3.0078124999999987e-05, "loss": 1.900078572332859, "policyLoss": -0.00011837753118015826, "valueLoss": 3.81856769323349, "entropy": 0.9086887426674366, "approximateKl": 3.606568498071283e-06, "clipFraction": 0.0, "explainedVariance": 0.8749983307163053, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 46641, "recentEpisodeCount": 100, "recentReturnMean": 127.46875932049385, "recentReturnMedian": 130.0977013478987, "recentLengthMean": 50.32, "recentLandingRate": 0.99 }, { "update": 693, "trainingStep": 2838528, "elapsedSeconds": 115.42198387498502, "environmentStepsPerSecond": 24592.61143071709, "learningRate": 2.968750000000001e-05, "loss": 2.273663453757763, "policyLoss": -6.180244963616133e-05, "valueLoss": 4.5654963701963425, "entropy": 0.9022917486727238, "approximateKl": 3.0115843401290476e-06, "clipFraction": 0.0, "explainedVariance": 0.8435673728242192, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 46724, "recentEpisodeCount": 100, "recentReturnMean": 129.72270971381812, "recentReturnMedian": 129.982456746744, "recentLengthMean": 50.3, "recentLandingRate": 1.0 }, { "update": 694, "trainingStep": 2842624, "elapsedSeconds": 115.57918733300176, "environmentStepsPerSecond": 24594.60103149847, "learningRate": 2.9296875e-05, "loss": 43.68110930919647, "policyLoss": -0.00018583470955491066, "valueLoss": 87.38050866127014, "entropy": 0.896011371165514, "approximateKl": 7.356989954132587e-06, "clipFraction": 0.0, "explainedVariance": 0.20211158848058064, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 46807, "recentEpisodeCount": 100, "recentReturnMean": 125.19195536576925, "recentReturnMedian": 129.86298795510083, "recentLengthMean": 49.89, "recentLandingRate": 0.98 }, { "update": 695, "trainingStep": 2846720, "elapsedSeconds": 115.7380517499987, "environmentStepsPerSecond": 24596.23224131239, "learningRate": 2.8906249999999988e-05, "loss": 2.4257262498140335, "policyLoss": -7.455915329046547e-05, "valueLoss": 4.869513660669327, "entropy": 0.8955981358885765, "approximateKl": 7.71878330851905e-06, "clipFraction": 0.0, "explainedVariance": 0.8271075621148121, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 46887, "recentEpisodeCount": 100, "recentReturnMean": 129.71004510166946, "recentReturnMedian": 129.79843699093908, "recentLengthMean": 50.33, "recentLandingRate": 1.0 }, { "update": 696, "trainingStep": 2850816, "elapsedSeconds": 115.901265374996, "environmentStepsPerSecond": 24596.93594177982, "learningRate": 2.8515625000000007e-05, "loss": 22.69836401939392, "policyLoss": -9.134341962635517e-05, "valueLoss": 45.414854526519775, "entropy": 0.8972035981714725, "approximateKl": 7.762406312394887e-06, "clipFraction": 0.0, "explainedVariance": 0.3289488235743062, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 46972, "recentEpisodeCount": 100, "recentReturnMean": 127.23100320793964, "recentReturnMedian": 128.97458461711358, "recentLengthMean": 49.03, "recentLandingRate": 0.99 }, { "update": 697, "trainingStep": 2854912, "elapsedSeconds": 116.05728666597861, "environmentStepsPerSecond": 24599.162034665227, "learningRate": 2.8125e-05, "loss": 1.6192367300391197, "policyLoss": -0.00011348165571689606, "valueLoss": 3.2569461911916733, "entropy": 0.9122915863990784, "approximateKl": 2.3088981834007427e-05, "clipFraction": 0.0, "explainedVariance": 0.8796924265606926, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 47056, "recentEpisodeCount": 100, "recentReturnMean": 129.22162525195756, "recentReturnMedian": 129.29366150358692, "recentLengthMean": 48.92, "recentLandingRate": 1.0 }, { "update": 698, "trainingStep": 2859008, "elapsedSeconds": 116.21328424999956, "environmentStepsPerSecond": 24601.38716886844, "learningRate": 2.7734374999999988e-05, "loss": 1.6002155244350433, "policyLoss": -0.0003343829303048551, "valueLoss": 3.2190753519535065, "entropy": 0.8987756706774235, "approximateKl": 2.3121545382309705e-05, "clipFraction": 0.0, "explainedVariance": 0.8945345850793238, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 47138, "recentEpisodeCount": 100, "recentReturnMean": 129.53619013991846, "recentReturnMedian": 129.6970795702655, "recentLengthMean": 49.27, "recentLandingRate": 1.0 }, { "update": 699, "trainingStep": 2863104, "elapsedSeconds": 116.36717574999784, "environmentStepsPerSecond": 24604.051628365254, "learningRate": 2.7343750000000007e-05, "loss": 1.5398223549127579, "policyLoss": -0.0001261458091903478, "valueLoss": 3.0977343320846558, "entropy": 0.8918657004833221, "approximateKl": 2.188109647249803e-05, "clipFraction": 0.0, "explainedVariance": 0.886398784424794, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 47222, "recentEpisodeCount": 100, "recentReturnMean": 129.739746827074, "recentReturnMedian": 129.8773642948363, "recentLengthMean": 50.37, "recentLandingRate": 1.0 }, { "update": 700, "trainingStep": 2867200, "elapsedSeconds": 116.51880395799526, "environmentStepsPerSecond": 24607.187017072527, "learningRate": 2.6953124999999996e-05, "loss": 23.377121448516846, "policyLoss": -0.00015858370170462877, "valueLoss": 46.77265548706055, "entropy": 0.9047759026288986, "approximateKl": 2.9509719752240926e-05, "clipFraction": 0.0, "explainedVariance": 0.29712206084054893, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 47302, "recentEpisodeCount": 100, "recentReturnMean": 127.8692360269052, "recentReturnMedian": 130.24008971918374, "recentLengthMean": 49.89, "recentLandingRate": 0.99 }, { "update": 701, "trainingStep": 2871296, "elapsedSeconds": 116.67616224999074, "environmentStepsPerSecond": 24609.105618746282, "learningRate": 2.6562499999999985e-05, "loss": 22.57076185941696, "policyLoss": 1.8799444660544395e-05, "valueLoss": 45.159472703933716, "entropy": 0.8993187993764877, "approximateKl": 2.5947396352421492e-05, "clipFraction": 0.0, "explainedVariance": 0.328216865827616, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 47385, "recentEpisodeCount": 100, "recentReturnMean": 125.16557982431004, "recentReturnMedian": 129.81036425707862, "recentLengthMean": 49.86, "recentLandingRate": 0.98 }, { "update": 702, "trainingStep": 2875392, "elapsedSeconds": 116.85285558298347, "environmentStepsPerSecond": 24606.946793508443, "learningRate": 2.6171875000000008e-05, "loss": 1.6186218187212944, "policyLoss": -0.00011957844253629446, "valueLoss": 3.2555949091911316, "entropy": 0.9056055285036564, "approximateKl": 4.771693056682125e-06, "clipFraction": 0.0, "explainedVariance": 0.8840505272401413, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 47466, "recentEpisodeCount": 100, "recentReturnMean": 129.5998932976854, "recentReturnMedian": 129.61797765328083, "recentLengthMean": 50.03, "recentLandingRate": 1.0 }, { "update": 703, "trainingStep": 2879488, "elapsedSeconds": 117.01381904099253, "environmentStepsPerSecond": 24608.102048111527, "learningRate": 2.5781249999999996e-05, "loss": 1.500260315835476, "policyLoss": -4.373720730654895e-05, "valueLoss": 3.0186152160167694, "entropy": 0.9003551825881004, "approximateKl": 3.3653232094366103e-06, "clipFraction": 0.0, "explainedVariance": 0.8879044442261047, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 47545, "recentEpisodeCount": 100, "recentReturnMean": 129.51453715531142, "recentReturnMedian": 129.42555577401072, "recentLengthMean": 50.71, "recentLandingRate": 1.0 }, { "update": 704, "trainingStep": 2883584, "elapsedSeconds": 117.16648012498626, "environmentStepsPerSecond": 24610.99793152413, "learningRate": 2.5390624999999985e-05, "loss": 22.862584233283997, "policyLoss": -0.00016905780648812652, "valueLoss": 45.743604242801666, "entropy": 0.904852457344532, "approximateKl": 1.5176894521573558e-05, "clipFraction": 0.0, "explainedVariance": 0.3291486209618102, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 47629, "recentEpisodeCount": 100, "recentReturnMean": 127.82415838673275, "recentReturnMedian": 130.00986285926774, "recentLengthMean": 50.07, "recentLandingRate": 0.99 }, { "update": 705, "trainingStep": 2887680, "elapsedSeconds": 117.32032987498678, "environmentStepsPerSecond": 24613.636895472675, "learningRate": 2.5000000000000008e-05, "loss": 22.966415405273438, "policyLoss": -0.00012086718925274909, "valueLoss": 45.95090568065643, "entropy": 0.8916475474834442, "approximateKl": 4.888042894890532e-05, "clipFraction": 0.0, "explainedVariance": 0.3264625038101907, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 47710, "recentEpisodeCount": 100, "recentReturnMean": 127.47564567417452, "recentReturnMedian": 129.8030232070014, "recentLengthMean": 49.33, "recentLandingRate": 0.99 }, { "update": 706, "trainingStep": 2891776, "elapsedSeconds": 117.47196220798651, "environmentStepsPerSecond": 24616.733607293045, "learningRate": 2.4609374999999997e-05, "loss": 21.985512673854828, "policyLoss": -0.00024408305762335658, "valueLoss": 43.98956322669983, "entropy": 0.9025109298527241, "approximateKl": 4.428918691701256e-05, "clipFraction": 0.0, "explainedVariance": 0.33610162505209973, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 47794, "recentEpisodeCount": 100, "recentReturnMean": 127.80636524038891, "recentReturnMedian": 130.09326825093012, "recentLengthMean": 50.02, "recentLandingRate": 0.99 }, { "update": 707, "trainingStep": 2895872, "elapsedSeconds": 117.62815174998832, "environmentStepsPerSecond": 24618.868501436667, "learningRate": 2.4218749999999986e-05, "loss": 24.299546033143997, "policyLoss": -0.000351590831996873, "valueLoss": 48.61779701709747, "entropy": 0.9001281447708607, "approximateKl": 8.285854346468113e-05, "clipFraction": 0.0, "explainedVariance": 0.3080873983115253, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 47877, "recentEpisodeCount": 100, "recentReturnMean": 127.42974442411592, "recentReturnMedian": 129.54661883844528, "recentLengthMean": 49.31, "recentLandingRate": 0.99 }, { "update": 708, "trainingStep": 2899968, "elapsedSeconds": 117.77806779099046, "environmentStepsPerSecond": 24622.309181929333, "learningRate": 2.3828125000000008e-05, "loss": 61.40886831283569, "policyLoss": -1.590175088495016e-06, "valueLoss": 122.83565425872803, "entropy": 0.8957040198147297, "approximateKl": 2.1867588657187298e-05, "clipFraction": 0.0, "explainedVariance": 0.1340573725910802, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 47960, "recentEpisodeCount": 100, "recentReturnMean": 123.2069589343197, "recentReturnMedian": 129.40809906367213, "recentLengthMean": 49.26, "recentLandingRate": 0.97 }, { "update": 709, "trainingStep": 2904064, "elapsedSeconds": 117.92911412499961, "environmentStepsPerSecond": 24625.5050887758, "learningRate": 2.3437499999999997e-05, "loss": 43.14640724658966, "policyLoss": -0.00024789373856037855, "valueLoss": 86.31112766265869, "entropy": 0.8908420689404011, "approximateKl": 2.0041850802954286e-05, "clipFraction": 0.0, "explainedVariance": 0.1874890879353477, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 48045, "recentEpisodeCount": 100, "recentReturnMean": 123.34457867199541, "recentReturnMedian": 129.66074161673896, "recentLengthMean": 49.07, "recentLandingRate": 0.97 }, { "update": 710, "trainingStep": 2908160, "elapsedSeconds": 118.079085165984, "environmentStepsPerSecond": 24628.917101720377, "learningRate": 2.3046874999999986e-05, "loss": 22.564038515090942, "policyLoss": -7.149085286073387e-05, "valueLoss": 45.146429657936096, "entropy": 0.9104790277779102, "approximateKl": 2.4914170353440568e-05, "clipFraction": 0.0, "explainedVariance": 0.33721112464187475, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 48129, "recentEpisodeCount": 100, "recentReturnMean": 127.03640964293736, "recentReturnMedian": 129.46120059350505, "recentLengthMean": 48.21, "recentLandingRate": 0.99 }, { "update": 711, "trainingStep": 2912256, "elapsedSeconds": 118.23483799997484, "environmentStepsPerSecond": 24631.115915265345, "learningRate": 2.265625000000001e-05, "loss": 15.803211636841297, "policyLoss": -3.577067400328815e-05, "valueLoss": 31.62434747815132, "entropy": 0.892623707652092, "approximateKl": 4.5915185182821006e-06, "clipFraction": 0.0, "explainedVariance": 0.42188591331532743, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 48209, "recentEpisodeCount": 100, "recentReturnMean": 127.73040214071, "recentReturnMedian": 130.0977483364186, "recentLengthMean": 49.17, "recentLandingRate": 0.99 }, { "update": 712, "trainingStep": 2916352, "elapsedSeconds": 118.40670679099276, "environmentStepsPerSecond": 24629.956182700353, "learningRate": 2.2265624999999997e-05, "loss": 2.1446337550878525, "policyLoss": -2.4899563868530095e-05, "valueLoss": 4.30725371837616, "entropy": 0.896819606423378, "approximateKl": 1.7381389625370502e-06, "clipFraction": 0.0, "explainedVariance": 0.8625994734628106, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 48294, "recentEpisodeCount": 100, "recentReturnMean": 129.56375303855165, "recentReturnMedian": 129.57199317635968, "recentLengthMean": 49.44, "recentLandingRate": 1.0 }, { "update": 713, "trainingStep": 2920448, "elapsedSeconds": 118.55989933299134, "environmentStepsPerSecond": 24632.679484633594, "learningRate": 2.1874999999999986e-05, "loss": 17.35000117123127, "policyLoss": -0.00018030288629233837, "valueLoss": 34.71823638677597, "entropy": 0.8936776556074619, "approximateKl": 1.2953947589267045e-05, "clipFraction": 0.0, "explainedVariance": 0.37016260732036077, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 48374, "recentEpisodeCount": 100, "recentReturnMean": 127.71998276235477, "recentReturnMedian": 129.88100985321216, "recentLengthMean": 49.93, "recentLandingRate": 0.99 }, { "update": 714, "trainingStep": 2924544, "elapsedSeconds": 118.7124372079852, "environmentStepsPerSecond": 24635.531615581054, "learningRate": 2.148437500000001e-05, "loss": 44.09171736240387, "policyLoss": 0.00015968759544193745, "valueLoss": 88.20105123519897, "entropy": 0.8967860825359821, "approximateKl": 8.478189556626603e-06, "clipFraction": 0.0, "explainedVariance": 0.19379569166145705, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 48459, "recentEpisodeCount": 100, "recentReturnMean": 125.43017248407658, "recentReturnMedian": 129.58526122385229, "recentLengthMean": 49.76, "recentLandingRate": 0.98 }, { "update": 715, "trainingStep": 2928640, "elapsedSeconds": 118.86481658299454, "environmentStepsPerSecond": 24638.409280303284, "learningRate": 2.1093749999999998e-05, "loss": 1.6902320459485054, "policyLoss": -2.6522917323745787e-05, "valueLoss": 3.398657739162445, "entropy": 0.9070294536650181, "approximateKl": 1.7991660570260137e-06, "clipFraction": 0.0, "explainedVariance": 0.8926068264158427, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 48541, "recentEpisodeCount": 100, "recentReturnMean": 129.52145944366464, "recentReturnMedian": 129.77340726263355, "recentLengthMean": 49.02, "recentLandingRate": 1.0 }, { "update": 716, "trainingStep": 2932736, "elapsedSeconds": 119.02322774997447, "environmentStepsPerSecond": 24640.030819535805, "learningRate": 2.0703124999999987e-05, "loss": 23.99143072962761, "policyLoss": -0.00010509896674193442, "valueLoss": 48.000972032547, "entropy": 0.8949907794594765, "approximateKl": 2.8167669370304793e-06, "clipFraction": 0.0, "explainedVariance": 0.2875647295277328, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 48624, "recentEpisodeCount": 100, "recentReturnMean": 127.35533250066347, "recentReturnMedian": 129.54182107147062, "recentLengthMean": 50.39, "recentLandingRate": 0.99 }, { "update": 717, "trainingStep": 2936832, "elapsedSeconds": 119.18123687498155, "environmentStepsPerSecond": 24641.731173512413, "learningRate": 2.031250000000001e-05, "loss": 1.7635606080293655, "policyLoss": -0.0002162253949791193, "valueLoss": 3.5455788671970367, "entropy": 0.9012583158910275, "approximateKl": 1.4146979083307087e-05, "clipFraction": 0.0, "explainedVariance": 0.8692450803810668, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 48704, "recentEpisodeCount": 100, "recentReturnMean": 129.22339310966782, "recentReturnMedian": 129.86531091679353, "recentLengthMean": 49.44, "recentLandingRate": 1.0 }, { "update": 718, "trainingStep": 2940928, "elapsedSeconds": 119.33548224999686, "environmentStepsPerSecond": 24644.204259710674, "learningRate": 1.9921874999999998e-05, "loss": 50.53692698478699, "policyLoss": 1.1772062862291932e-05, "valueLoss": 101.09176683425903, "entropy": 0.8967705816030502, "approximateKl": 7.472812285413966e-06, "clipFraction": 0.0, "explainedVariance": 0.16164814521537518, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 48789, "recentEpisodeCount": 100, "recentReturnMean": 123.03604447941645, "recentReturnMedian": 129.6101859100163, "recentLengthMean": 49.08, "recentLandingRate": 0.97 }, { "update": 719, "trainingStep": 2945024, "elapsedSeconds": 119.49592095799744, "environmentStepsPerSecond": 24645.39355310019, "learningRate": 1.9531249999999987e-05, "loss": 64.06744146347046, "policyLoss": -0.00011630624067038298, "valueLoss": 128.15312957763672, "entropy": 0.9008488580584526, "approximateKl": 1.85887620318681e-06, "clipFraction": 0.0, "explainedVariance": 0.12173801615258528, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 48870, "recentEpisodeCount": 100, "recentReturnMean": 122.91352433299996, "recentReturnMedian": 129.55776493437588, "recentLengthMean": 49.31, "recentLandingRate": 0.97 }, { "update": 720, "trainingStep": 2949120, "elapsedSeconds": 119.65425187497749, "environmentStepsPerSecond": 24647.013823473917, "learningRate": 1.914062500000001e-05, "loss": 23.497013568878174, "policyLoss": -8.807514677755535e-05, "valueLoss": 47.01220524311066, "entropy": 0.9001048877835274, "approximateKl": 8.370247087441385e-06, "clipFraction": 0.0, "explainedVariance": 0.3172303313114735, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 48953, "recentEpisodeCount": 100, "recentReturnMean": 127.66319303197612, "recentReturnMedian": 130.00073167681694, "recentLengthMean": 49.91, "recentLandingRate": 0.99 }, { "update": 721, "trainingStep": 2953216, "elapsedSeconds": 119.80759987499914, "environmentStepsPerSecond": 24649.654972482782, "learningRate": 1.875e-05, "loss": 21.32424660027027, "policyLoss": -0.00014154502423480153, "valueLoss": 42.66672617197037, "entropy": 0.8975133672356606, "approximateKl": 2.0586783648468554e-05, "clipFraction": 0.0, "explainedVariance": 0.34775681850063356, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 49038, "recentEpisodeCount": 100, "recentReturnMean": 127.8626182534614, "recentReturnMedian": 130.2131135391537, "recentLengthMean": 49.36, "recentLandingRate": 0.99 }, { "update": 722, "trainingStep": 2957312, "elapsedSeconds": 119.96363670798019, "environmentStepsPerSecond": 24651.73681920627, "learningRate": 1.8359374999999987e-05, "loss": 42.54509699344635, "policyLoss": -8.779286872595549e-06, "valueLoss": 85.1081326007843, "entropy": 0.8960050232708454, "approximateKl": 1.7276037397095934e-05, "clipFraction": 0.0, "explainedVariance": 0.18645781162429587, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 49117, "recentEpisodeCount": 100, "recentReturnMean": 125.74879987479522, "recentReturnMedian": 130.31224965117872, "recentLengthMean": 49.97, "recentLandingRate": 0.98 }, { "update": 723, "trainingStep": 2961408, "elapsedSeconds": 120.13694304099772, "environmentStepsPerSecond": 24650.26930966102, "learningRate": 1.796875000000001e-05, "loss": 24.228725612163544, "policyLoss": -2.2036227164790034e-05, "valueLoss": 48.475263714790344, "entropy": 0.8884229063987732, "approximateKl": 7.942835509311408e-07, "clipFraction": 0.0, "explainedVariance": 0.2884443980639231, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 49198, "recentEpisodeCount": 100, "recentReturnMean": 127.751826436361, "recentReturnMedian": 130.54350494415849, "recentLengthMean": 50.63, "recentLandingRate": 0.99 }, { "update": 724, "trainingStep": 2965504, "elapsedSeconds": 120.29053425000166, "environmentStepsPerSecond": 24652.845865966043, "learningRate": 1.7578125e-05, "loss": 22.517620772123337, "policyLoss": -0.0004286584444344044, "valueLoss": 45.05430096387863, "entropy": 0.9101013615727425, "approximateKl": 6.041842789272778e-05, "clipFraction": 0.0, "explainedVariance": 0.32520456778038176, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 49279, "recentEpisodeCount": 100, "recentReturnMean": 127.05351666296018, "recentReturnMedian": 128.89445057907142, "recentLengthMean": 49.36, "recentLandingRate": 0.99 }, { "update": 725, "trainingStep": 2969600, "elapsedSeconds": 120.44285754099838, "environmentStepsPerSecond": 24655.67540183242, "learningRate": 1.7187499999999987e-05, "loss": 22.89671403169632, "policyLoss": -0.0002014204510487616, "valueLoss": 45.81162118911743, "entropy": 0.8895260766148567, "approximateKl": 6.68079883325845e-05, "clipFraction": 0.0, "explainedVariance": 0.31746872493318745, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 49362, "recentEpisodeCount": 100, "recentReturnMean": 125.09581743127302, "recentReturnMedian": 129.6315997085767, "recentLengthMean": 50.55, "recentLandingRate": 0.98 }, { "update": 726, "trainingStep": 2973696, "elapsedSeconds": 120.59810979099711, "environmentStepsPerSecond": 24657.898910302756, "learningRate": 1.679687500000001e-05, "loss": 1.7505162954330444, "policyLoss": 2.2005318896844983e-05, "valueLoss": 3.5191508531570435, "entropy": 0.9081103652715683, "approximateKl": 8.383856766158715e-06, "clipFraction": 0.0, "explainedVariance": 0.8814765614680161, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 49448, "recentEpisodeCount": 100, "recentReturnMean": 127.07769869899654, "recentReturnMedian": 129.02200630051084, "recentLengthMean": 48.98, "recentLandingRate": 0.99 }, { "update": 727, "trainingStep": 2977792, "elapsedSeconds": 120.75048379099462, "environmentStepsPerSecond": 24660.70450826698, "learningRate": 1.640625e-05, "loss": 44.73107600212097, "policyLoss": -6.261398084461689e-06, "valueLoss": 89.48039269447327, "entropy": 0.9114502891898155, "approximateKl": 3.2333264243789017e-07, "clipFraction": 0.0, "explainedVariance": 0.1693338420008209, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 49527, "recentEpisodeCount": 100, "recentReturnMean": 125.03439731912331, "recentReturnMedian": 129.20972313638777, "recentLengthMean": 49.86, "recentLandingRate": 0.98 }, { "update": 728, "trainingStep": 2981888, "elapsedSeconds": 120.89997133298311, "environmentStepsPerSecond": 24664.09186969345, "learningRate": 1.6015624999999988e-05, "loss": 23.60821759700775, "policyLoss": -0.00030287064146250486, "valueLoss": 47.235029339790344, "entropy": 0.8993923291563988, "approximateKl": 2.9716542485402897e-05, "clipFraction": 0.0, "explainedVariance": 0.32000473177492306, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 49612, "recentEpisodeCount": 100, "recentReturnMean": 127.20898040541616, "recentReturnMedian": 129.56648800137918, "recentLengthMean": 49.44, "recentLandingRate": 0.99 }, { "update": 729, "trainingStep": 2985984, "elapsedSeconds": 121.0515992079745, "environmentStepsPerSecond": 24667.034715253, "learningRate": 1.562500000000001e-05, "loss": 22.97859588265419, "policyLoss": -0.00017240276793017983, "valueLoss": 45.97564470767975, "entropy": 0.9053822159767151, "approximateKl": 4.6610584831796587e-05, "clipFraction": 0.0, "explainedVariance": 0.32238329381006137, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 49694, "recentEpisodeCount": 100, "recentReturnMean": 127.19943121505537, "recentReturnMedian": 129.36563439294696, "recentLengthMean": 50.12, "recentLandingRate": 0.99 }, { "update": 730, "trainingStep": 2990080, "elapsedSeconds": 121.20308062498225, "environmentStepsPerSecond": 24670.00000809953, "learningRate": 1.5234375e-05, "loss": 57.53924310207367, "policyLoss": -8.52504454087466e-05, "valueLoss": 115.09656977653503, "entropy": 0.8956653773784637, "approximateKl": 2.6488305593375117e-06, "clipFraction": 0.0, "explainedVariance": 0.14043395053680907, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 49774, "recentEpisodeCount": 100, "recentReturnMean": 123.02740470803693, "recentReturnMedian": 129.81108841625974, "recentLengthMean": 49.75, "recentLandingRate": 0.97 }, { "update": 731, "trainingStep": 2994176, "elapsedSeconds": 121.3562322910002, "environmentStepsPerSecond": 24672.618319430545, "learningRate": 1.4843749999999988e-05, "loss": 23.22952175140381, "policyLoss": -0.00011076088412664831, "valueLoss": 46.47687739133835, "entropy": 0.8806016221642494, "approximateKl": 6.996742740739137e-06, "clipFraction": 0.0, "explainedVariance": 0.3362877494498203, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 49859, "recentEpisodeCount": 100, "recentReturnMean": 127.51900842905474, "recentReturnMedian": 129.94568780995905, "recentLengthMean": 49.47, "recentLandingRate": 0.99 }, { "update": 732, "trainingStep": 2998272, "elapsedSeconds": 121.50927308297832, "environmentStepsPerSecond": 24675.252545972264, "learningRate": 1.4453125000000009e-05, "loss": 2.4105850160121918, "policyLoss": -4.3241074308753014e-05, "valueLoss": 4.839414894580841, "entropy": 0.9079187624156475, "approximateKl": 3.396886313566938e-06, "clipFraction": 0.0, "explainedVariance": 0.822389068595454, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 49939, "recentEpisodeCount": 100, "recentReturnMean": 129.5020847159583, "recentReturnMedian": 129.87215091334656, "recentLengthMean": 50.17, "recentLandingRate": 1.0 }, { "update": 733, "trainingStep": 3002368, "elapsedSeconds": 121.66255320797791, "environmentStepsPerSecond": 24677.831599239547, "learningRate": 1.40625e-05, "loss": 1.9453924372792244, "policyLoss": -2.8685637516900897e-05, "valueLoss": 3.9090656042099, "entropy": 0.9111655689775944, "approximateKl": 8.760544005781412e-07, "clipFraction": 0.0, "explainedVariance": 0.868134914814463, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 50027, "recentEpisodeCount": 100, "recentReturnMean": 129.30333408155192, "recentReturnMedian": 129.45448712656253, "recentLengthMean": 49.59, "recentLandingRate": 1.0 }, { "update": 734, "trainingStep": 3006464, "elapsedSeconds": 121.81227158298134, "environmentStepsPerSecond": 24681.125808838784, "learningRate": 1.3671874999999988e-05, "loss": 23.104504764080048, "policyLoss": -9.431468788534403e-05, "valueLoss": 46.22717523574829, "entropy": 0.8988520540297031, "approximateKl": 2.9227703635115176e-06, "clipFraction": 0.0, "explainedVariance": 0.3252137965750228, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 50104, "recentEpisodeCount": 100, "recentReturnMean": 127.0453154736977, "recentReturnMedian": 129.19397616991773, "recentLengthMean": 49.12, "recentLandingRate": 0.99 }, { "update": 735, "trainingStep": 3010560, "elapsedSeconds": 121.96308429099736, "environmentStepsPerSecond": 24684.190445831675, "learningRate": 1.328125000000001e-05, "loss": 44.97421622276306, "policyLoss": -0.00018526826170273125, "valueLoss": 89.96694707870483, "entropy": 0.9072099439799786, "approximateKl": 1.2039661669405177e-05, "clipFraction": 0.0, "explainedVariance": 0.17081883654348573, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 50190, "recentEpisodeCount": 100, "recentReturnMean": 125.1287174054049, "recentReturnMedian": 129.50412883842364, "recentLengthMean": 49.5, "recentLandingRate": 0.98 }, { "update": 736, "trainingStep": 3014656, "elapsedSeconds": 122.11964266598807, "environmentStepsPerSecond": 24686.08599064974, "learningRate": 1.2890624999999998e-05, "loss": 1.9572010040283203, "policyLoss": -5.681868060491979e-06, "valueLoss": 3.9323810636997223, "entropy": 0.8983826451003551, "approximateKl": 3.2949974411167204e-06, "clipFraction": 0.0, "explainedVariance": 0.8775377799728853, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 50272, "recentEpisodeCount": 100, "recentReturnMean": 127.55314697668116, "recentReturnMedian": 129.91927163721994, "recentLengthMean": 49.42, "recentLandingRate": 0.99 }, { "update": 737, "trainingStep": 3018752, "elapsedSeconds": 122.27911462498014, "environmentStepsPerSecond": 24687.388433080014, "learningRate": 1.2499999999999987e-05, "loss": 40.26474750041962, "policyLoss": -1.2520788004621863e-05, "valueLoss": 80.54746675491333, "entropy": 0.8972748890519142, "approximateKl": 6.406953616533428e-07, "clipFraction": 0.0, "explainedVariance": 0.20099652488746045, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 50354, "recentEpisodeCount": 100, "recentReturnMean": 125.85355937212938, "recentReturnMedian": 130.0807518803049, "recentLengthMean": 50.25, "recentLandingRate": 0.98 }, { "update": 738, "trainingStep": 3022848, "elapsedSeconds": 122.44416308298241, "environmentStepsPerSecond": 24687.56308090706, "learningRate": 1.210937500000001e-05, "loss": 23.72518116235733, "policyLoss": -0.00019165551930200309, "valueLoss": 47.46864140033722, "entropy": 0.8948034308850765, "approximateKl": 1.76732792169787e-05, "clipFraction": 0.0, "explainedVariance": 0.30162845170852426, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 50432, "recentEpisodeCount": 100, "recentReturnMean": 125.38814568624657, "recentReturnMedian": 129.37615394894965, "recentLengthMean": 50.48, "recentLandingRate": 0.98 }, { "update": 739, "trainingStep": 3026944, "elapsedSeconds": 122.61433833299088, "environmentStepsPerSecond": 24686.70500655113, "learningRate": 1.1718749999999999e-05, "loss": 43.33632934093475, "policyLoss": -0.00013041586498729885, "valueLoss": 86.69082617759705, "entropy": 0.8952653370797634, "approximateKl": 1.5463163435924798e-05, "clipFraction": 0.0, "explainedVariance": 0.19079134090336902, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 50518, "recentEpisodeCount": 100, "recentReturnMean": 125.05049303866835, "recentReturnMedian": 129.28593020420521, "recentLengthMean": 49.97, "recentLandingRate": 0.98 }, { "update": 740, "trainingStep": 3031040, "elapsedSeconds": 122.77074133299175, "environmentStepsPerSecond": 24688.618534760604, "learningRate": 1.1328124999999987e-05, "loss": 43.4070543050766, "policyLoss": -5.619949661195278e-06, "valueLoss": 86.83203387260437, "entropy": 0.8956500887870789, "approximateKl": 1.0399380698800087e-06, "clipFraction": 0.0, "explainedVariance": 0.18247901722457538, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 50597, "recentEpisodeCount": 100, "recentReturnMean": 124.86857020622446, "recentReturnMedian": 129.19984646742523, "recentLengthMean": 49.48, "recentLandingRate": 0.98 }, { "update": 741, "trainingStep": 3035136, "elapsedSeconds": 122.92504541599192, "environmentStepsPerSecond": 24690.94877881692, "learningRate": 1.093750000000001e-05, "loss": 14.309927567839622, "policyLoss": -0.0001230149355251342, "valueLoss": 28.637983709573746, "entropy": 0.8941385522484779, "approximateKl": 5.24220013176091e-06, "clipFraction": 0.0, "explainedVariance": 0.43828703063699836, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 50682, "recentEpisodeCount": 100, "recentReturnMean": 127.13465246409935, "recentReturnMedian": 129.24894233437954, "recentLengthMean": 50.21, "recentLandingRate": 0.99 }, { "update": 742, "trainingStep": 3039232, "elapsedSeconds": 123.08133270798135, "environmentStepsPerSecond": 24692.875297432634, "learningRate": 1.0546874999999999e-05, "loss": 14.114110343158245, "policyLoss": -4.315901605878025e-05, "valueLoss": 28.246435523033142, "entropy": 0.9064416103065014, "approximateKl": 3.7794925447087735e-06, "clipFraction": 0.0, "explainedVariance": 0.4383292065402399, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 50762, "recentEpisodeCount": 100, "recentReturnMean": 127.15991851383296, "recentReturnMedian": 129.24165166402236, "recentLengthMean": 50.29, "recentLandingRate": 0.99 }, { "update": 743, "trainingStep": 3043328, "elapsedSeconds": 123.23823291598819, "environmentStepsPerSecond": 24694.674112007466, "learningRate": 1.0156249999999988e-05, "loss": 40.429569602012634, "policyLoss": -2.1208717953413725e-05, "valueLoss": 80.87715983390808, "entropy": 0.8989186361432076, "approximateKl": 1.1079682735726237e-06, "clipFraction": 0.0, "explainedVariance": 0.1812025809919232, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 50844, "recentEpisodeCount": 100, "recentReturnMean": 124.92964214649575, "recentReturnMedian": 129.09940977708902, "recentLengthMean": 49.01, "recentLandingRate": 0.98 }, { "update": 744, "trainingStep": 3047424, "elapsedSeconds": 123.394813040999, "environmentStepsPerSecond": 24696.53241410939, "learningRate": 9.76562500000001e-06, "loss": 1.2706444561481476, "policyLoss": -1.4291319530457258e-05, "valueLoss": 2.5594455152750015, "entropy": 0.9063993096351624, "approximateKl": 3.5482662497088313e-07, "clipFraction": 0.0, "explainedVariance": 0.9145814477051757, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 50928, "recentEpisodeCount": 100, "recentReturnMean": 129.1707209127843, "recentReturnMedian": 128.8887860077666, "recentLengthMean": 49.32, "recentLandingRate": 1.0 }, { "update": 745, "trainingStep": 3051520, "elapsedSeconds": 123.55097499999101, "environmentStepsPerSecond": 24698.469599290675, "learningRate": 9.375e-06, "loss": 27.503926426172256, "policyLoss": -2.0210136426612735e-05, "valueLoss": 55.0261065363884, "entropy": 0.9106825478374958, "approximateKl": 4.108151188120246e-07, "clipFraction": 0.0, "explainedVariance": 0.28260887083896813, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 51010, "recentEpisodeCount": 100, "recentReturnMean": 124.96335119703843, "recentReturnMedian": 129.1414771238342, "recentLengthMean": 48.98, "recentLandingRate": 0.98 }, { "update": 746, "trainingStep": 3055616, "elapsedSeconds": 123.71719387499616, "environmentStepsPerSecond": 24698.39400889899, "learningRate": 8.984374999999988e-06, "loss": 22.780709385871887, "policyLoss": -7.421078043989837e-05, "valueLoss": 45.579549908638, "entropy": 0.89911088347435, "approximateKl": 4.715493560070172e-06, "clipFraction": 0.0, "explainedVariance": 0.32969489637480975, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 51097, "recentEpisodeCount": 100, "recentReturnMean": 127.37219362610023, "recentReturnMedian": 129.51456546853296, "recentLengthMean": 49.29, "recentLandingRate": 0.99 }, { "update": 747, "trainingStep": 3059712, "elapsedSeconds": 123.87391108297743, "environmentStepsPerSecond": 24700.21308966696, "learningRate": 8.59375000000001e-06, "loss": 2.260435350239277, "policyLoss": -2.8368202038109303e-05, "valueLoss": 4.538962170481682, "entropy": 0.9017362892627716, "approximateKl": 2.879307430703193e-06, "clipFraction": 0.0, "explainedVariance": 0.8436624405180133, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 51177, "recentEpisodeCount": 100, "recentReturnMean": 129.25192629875878, "recentReturnMedian": 129.07825832394883, "recentLengthMean": 49.7, "recentLandingRate": 1.0 }, { "update": 748, "trainingStep": 3063808, "elapsedSeconds": 124.0439233329962, "environmentStepsPerSecond": 24699.380007315638, "learningRate": 8.203125e-06, "loss": 61.47011470794678, "policyLoss": 1.0149786248803139e-05, "valueLoss": 122.95812320709229, "entropy": 0.8956727907061577, "approximateKl": 6.553818820975721e-08, "clipFraction": 0.0, "explainedVariance": 0.1349844401705741, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 51263, "recentEpisodeCount": 100, "recentReturnMean": 123.25624030834821, "recentReturnMedian": 129.61528774237377, "recentLengthMean": 50.01, "recentLandingRate": 0.97 }, { "update": 749, "trainingStep": 3067904, "elapsedSeconds": 124.21166958299, "environmentStepsPerSecond": 24698.99978238542, "learningRate": 7.812499999999988e-06, "loss": 20.380411446094513, "policyLoss": -4.650471964851022e-05, "valueLoss": 40.77876269817352, "entropy": 0.8923103660345078, "approximateKl": 1.1797565093729645e-06, "clipFraction": 0.0, "explainedVariance": 0.35666201438013845, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 51343, "recentEpisodeCount": 100, "recentReturnMean": 127.60592426460586, "recentReturnMedian": 129.66306108550634, "recentLengthMean": 49.22, "recentLandingRate": 0.99 }, { "update": 750, "trainingStep": 3072000, "elapsedSeconds": 124.36688774998765, "environmentStepsPerSecond": 24701.1085955257, "learningRate": 7.42187500000001e-06, "loss": 22.227595388889313, "policyLoss": -3.4423486795276403e-05, "valueLoss": 44.47318887710571, "entropy": 0.8964781425893307, "approximateKl": 5.235451681073755e-07, "clipFraction": 0.0, "explainedVariance": 0.3454340507438378, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 51425, "recentEpisodeCount": 100, "recentReturnMean": 127.24210478602646, "recentReturnMedian": 129.51437362935394, "recentLengthMean": 48.84, "recentLandingRate": 0.99 }, { "update": 751, "trainingStep": 3076096, "elapsedSeconds": 124.52103445798275, "environmentStepsPerSecond": 24703.42471366129, "learningRate": 7.03125e-06, "loss": 22.459046244621277, "policyLoss": -1.1877695214934647e-05, "valueLoss": 44.93632733821869, "entropy": 0.910551656037569, "approximateKl": 4.795074346475303e-07, "clipFraction": 0.0, "explainedVariance": 0.34138595076113953, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 51510, "recentEpisodeCount": 100, "recentReturnMean": 127.2995253823555, "recentReturnMedian": 129.65411479352042, "recentLengthMean": 49.18, "recentLandingRate": 0.99 }, { "update": 752, "trainingStep": 3080192, "elapsedSeconds": 124.68395504099317, "environmentStepsPerSecond": 24703.99658871348, "learningRate": 6.640624999999989e-06, "loss": 23.326231002807617, "policyLoss": 2.0500709069892764e-05, "valueLoss": 46.670427083969116, "entropy": 0.9003130830824375, "approximateKl": 1.4965698937885463e-06, "clipFraction": 0.0, "explainedVariance": 0.289914173023036, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 51590, "recentEpisodeCount": 100, "recentReturnMean": 127.29149418161141, "recentReturnMedian": 129.45163137512282, "recentLengthMean": 50.51, "recentLandingRate": 0.99 }, { "update": 753, "trainingStep": 3084288, "elapsedSeconds": 124.85257754099439, "environmentStepsPerSecond": 24703.438733471863, "learningRate": 6.2500000000000105e-06, "loss": 1.4740155935287476, "policyLoss": -5.778152262791991e-05, "valueLoss": 2.966509163379669, "entropy": 0.9181195572018623, "approximateKl": 9.87150997389108e-07, "clipFraction": 0.0, "explainedVariance": 0.8937273523062075, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 51672, "recentEpisodeCount": 100, "recentReturnMean": 129.3675655266046, "recentReturnMedian": 129.17112320568413, "recentLengthMean": 50.18, "recentLandingRate": 1.0 }, { "update": 754, "trainingStep": 3088384, "elapsedSeconds": 125.02511604098254, "environmentStepsPerSecond": 24702.108646615012, "learningRate": 5.859374999999999e-06, "loss": 23.047445833683014, "policyLoss": -3.30408220179379e-05, "valueLoss": 46.11303198337555, "entropy": 0.9037292785942554, "approximateKl": 2.4023756850510836e-07, "clipFraction": 0.0, "explainedVariance": 0.33037429006560504, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 51756, "recentEpisodeCount": 100, "recentReturnMean": 127.63367916232978, "recentReturnMedian": 129.47632614232134, "recentLengthMean": 49.7, "recentLandingRate": 0.99 }, { "update": 755, "trainingStep": 3092480, "elapsedSeconds": 125.19585358299082, "environmentStepsPerSecond": 24701.137549655607, "learningRate": 5.468749999999988e-06, "loss": 26.09014981985092, "policyLoss": -2.697472518775612e-05, "valueLoss": 52.19831573963165, "entropy": 0.8981176726520061, "approximateKl": 9.760005923453718e-07, "clipFraction": 0.0, "explainedVariance": 0.2655377886956435, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 51833, "recentEpisodeCount": 100, "recentReturnMean": 123.12868188052133, "recentReturnMedian": 129.69012448564172, "recentLengthMean": 50.94, "recentLandingRate": 0.97 }, { "update": 756, "trainingStep": 3096576, "elapsedSeconds": 125.34930524998344, "environmentStepsPerSecond": 24703.5752916581, "learningRate": 5.078125000000011e-06, "loss": 12.692233979701996, "policyLoss": -5.0743139581754804e-05, "valueLoss": 25.402721524238586, "entropy": 0.9076057523488998, "approximateKl": 6.748268788214773e-07, "clipFraction": 0.0, "explainedVariance": 0.4443566706498615, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 51915, "recentEpisodeCount": 100, "recentReturnMean": 127.09608186722326, "recentReturnMedian": 129.2315574211534, "recentLengthMean": 50.87, "recentLandingRate": 0.99 }, { "update": 757, "trainingStep": 3100672, "elapsedSeconds": 125.50175399999716, "environmentStepsPerSecond": 24706.20450452087, "learningRate": 4.6875e-06, "loss": 2.0010864660143852, "policyLoss": -6.221933290362358e-06, "valueLoss": 4.020255699753761, "entropy": 0.9035173244774342, "approximateKl": 1.4829856809228659e-07, "clipFraction": 0.0, "explainedVariance": 0.8608693952537484, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 51995, "recentEpisodeCount": 100, "recentReturnMean": 129.77997945025942, "recentReturnMedian": 129.67048809770495, "recentLengthMean": 50.57, "recentLandingRate": 1.0 }, { "update": 758, "trainingStep": 3104768, "elapsedSeconds": 125.6527662909939, "environmentStepsPerSecond": 24709.109808293437, "learningRate": 4.296874999999988e-06, "loss": 29.767603158950806, "policyLoss": -4.1832594433799386e-05, "valueLoss": 59.553385734558105, "entropy": 0.904789749532938, "approximateKl": 8.499300747644156e-07, "clipFraction": 0.0, "explainedVariance": 0.26165004019375493, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 52079, "recentEpisodeCount": 100, "recentReturnMean": 125.5689616311976, "recentReturnMedian": 129.80482822738122, "recentLengthMean": 49.71, "recentLandingRate": 0.98 }, { "update": 759, "trainingStep": 3108864, "elapsedSeconds": 125.80546758297714, "environmentStepsPerSecond": 24711.67636612849, "learningRate": 3.906250000000011e-06, "loss": 1.6572699844837189, "policyLoss": -3.522145561873913e-07, "valueLoss": 3.3324199616909027, "entropy": 0.8939653225243092, "approximateKl": 5.88101102039218e-07, "clipFraction": 0.0, "explainedVariance": 0.9013815191037737, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 52163, "recentEpisodeCount": 100, "recentReturnMean": 129.82166502096996, "recentReturnMedian": 129.740607785061, "recentLengthMean": 48.84, "recentLandingRate": 1.0 }, { "update": 760, "trainingStep": 3112960, "elapsedSeconds": 125.95639024997945, "environmentStepsPerSecond": 24714.585689712618, "learningRate": 3.515625e-06, "loss": 22.756377309560776, "policyLoss": -7.110589649528265e-06, "valueLoss": 45.53110331296921, "entropy": 0.9166920818388462, "approximateKl": 1.8036735127680004e-07, "clipFraction": 0.0, "explainedVariance": 0.30725244381999306, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 52244, "recentEpisodeCount": 100, "recentReturnMean": 127.26747574915431, "recentReturnMedian": 129.92001499119215, "recentLengthMean": 49.57, "recentLandingRate": 0.99 }, { "update": 761, "trainingStep": 3117056, "elapsedSeconds": 126.11225616600132, "environmentStepsPerSecond": 24716.519193003933, "learningRate": 3.1249999999999887e-06, "loss": 2.1787674352526665, "policyLoss": -3.6834680940955877e-06, "valueLoss": 4.3756923377513885, "entropy": 0.9075036384165287, "approximateKl": 3.1623858376406133e-07, "clipFraction": 0.0, "explainedVariance": 0.8589921204472178, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 52325, "recentEpisodeCount": 100, "recentReturnMean": 129.62044946693584, "recentReturnMedian": 129.7755996864289, "recentLengthMean": 50.11, "recentLandingRate": 1.0 }, { "update": 762, "trainingStep": 3121152, "elapsedSeconds": 126.26541687498684, "environmentStepsPerSecond": 24718.977509813296, "learningRate": 2.734375000000011e-06, "loss": 21.993887156248093, "policyLoss": -2.165633486583829e-05, "valueLoss": 44.00588130950928, "entropy": 0.9031658172607422, "approximateKl": 1.9998333300463855e-07, "clipFraction": 0.0, "explainedVariance": 0.3421549780819434, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 52409, "recentEpisodeCount": 100, "recentReturnMean": 127.33450374778091, "recentReturnMedian": 129.9472423903644, "recentLengthMean": 49.68, "recentLandingRate": 0.99 }, { "update": 763, "trainingStep": 3125248, "elapsedSeconds": 126.43361745798029, "environmentStepsPerSecond": 24718.489139477984, "learningRate": 2.34375e-06, "loss": 23.17340439558029, "policyLoss": -6.954965647310019e-05, "valueLoss": 46.36484885215759, "entropy": 0.8950596898794174, "approximateKl": 5.87031536269933e-07, "clipFraction": 0.0, "explainedVariance": 0.3363467575295018, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 52493, "recentEpisodeCount": 100, "recentReturnMean": 125.24483679712662, "recentReturnMedian": 129.83004330820404, "recentLengthMean": 49.79, "recentLandingRate": 0.98 }, { "update": 764, "trainingStep": 3129344, "elapsedSeconds": 126.59450137498789, "environmentStepsPerSecond": 24719.430670456317, "learningRate": 1.9531249999999886e-06, "loss": 2.6578335016965866, "policyLoss": -2.4011824280023575e-06, "valueLoss": 5.333763390779495, "entropy": 0.9045758098363876, "approximateKl": 3.383393050171435e-07, "clipFraction": 0.0, "explainedVariance": 0.8042523771599583, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 52570, "recentEpisodeCount": 100, "recentReturnMean": 129.4113911635052, "recentReturnMedian": 129.2479831520468, "recentLengthMean": 51.33, "recentLandingRate": 1.0 }, { "update": 765, "trainingStep": 3133440, "elapsedSeconds": 126.75423424999462, "environmentStepsPerSecond": 24720.594294467388, "learningRate": 1.5625000000000109e-06, "loss": 2.186090409755707, "policyLoss": -3.528781235218048e-06, "valueLoss": 4.390366479754448, "entropy": 0.9089329205453396, "approximateKl": 4.557659849524498e-08, "clipFraction": 0.0, "explainedVariance": 0.843684313052643, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 52653, "recentEpisodeCount": 100, "recentReturnMean": 129.73415320522028, "recentReturnMedian": 129.74301714682952, "recentLengthMean": 50.99, "recentLandingRate": 1.0 }, { "update": 766, "trainingStep": 3137536, "elapsedSeconds": 126.9078331659839, "environmentStepsPerSecond": 24722.949889912536, "learningRate": 1.171875e-06, "loss": 1.6573999747633934, "policyLoss": -5.765628884546459e-06, "valueLoss": 3.332780286669731, "entropy": 0.8984405845403671, "approximateKl": 2.0354491425678134e-08, "clipFraction": 0.0, "explainedVariance": 0.8745636885699527, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 52734, "recentEpisodeCount": 100, "recentReturnMean": 129.55672368836392, "recentReturnMedian": 129.8782007660484, "recentLengthMean": 50.45, "recentLandingRate": 1.0 }, { "update": 767, "trainingStep": 3141632, "elapsedSeconds": 127.06157945797895, "environmentStepsPerSecond": 24725.27111186259, "learningRate": 7.812499999999888e-07, "loss": 1.9642675518989563, "policyLoss": -6.092246621847153e-06, "valueLoss": 3.946571484208107, "entropy": 0.9012105986475945, "approximateKl": 1.0793883120641112e-08, "clipFraction": 0.0, "explainedVariance": 0.8453335567086713, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 52815, "recentEpisodeCount": 100, "recentReturnMean": 129.28495604768116, "recentReturnMedian": 129.262447275687, "recentLengthMean": 50.33, "recentLandingRate": 1.0 }, { "update": 768, "trainingStep": 3145728, "elapsedSeconds": 127.21208166598808, "environmentStepsPerSecond": 24728.217310833097, "learningRate": 3.906250000000111e-07, "loss": 3.6197612285614014, "policyLoss": -3.356341039761901e-06, "valueLoss": 7.258029922842979, "entropy": 0.9250354431569576, "approximateKl": 1.9972503650933504e-09, "clipFraction": 0.0, "explainedVariance": 0.7650075481082004, "epochsCompleted": 4, "targetKlStoppedEpochs": false, "completedEpisodes": 52895, "recentEpisodeCount": 100, "recentReturnMean": 127.23545196194246, "recentReturnMedian": 129.51833098731004, "recentLengthMean": 49.7, "recentLandingRate": 0.99 } ] }