cha00's picture
First Push
e826adf
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.6728843450546265,
"min": 0.6356205344200134,
"max": 2.646869421005249,
"count": 10
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 33648.25390625,
"min": 31700.939453125,
"max": 133727.78125,
"count": 10
},
"SnowballTarget.Step.mean": {
"value": 499976.0,
"min": 49936.0,
"max": 499976.0,
"count": 10
},
"SnowballTarget.Step.sum": {
"value": 499976.0,
"min": 49936.0,
"max": 499976.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.367481231689453,
"min": 1.895678997039795,
"max": 12.367481231689453,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 12404.583984375,
"min": 1880.5135498046875,
"max": 12404.583984375,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 50347.0,
"min": 48158.0,
"max": 50347.0,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.03039761439419859,
"min": 0.02858054531463785,
"max": 0.03341945084389737,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.6991451310665676,
"min": 0.6573525422366705,
"max": 0.7686473694096395,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17709221018721227,
"min": 0.17493794429482834,
"max": 0.304932471094788,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 4.0731208343058825,
"min": 3.8486347744862237,
"max": 7.013446835180123,
"count": 10
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.4932895022400003e-05,
"min": 1.4932895022400003e-05,
"max": 0.00028487280504239996,
"count": 10
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.0003434565855152001,
"min": 0.0003434565855152001,
"max": 0.006267201710932799,
"count": 10
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10497759999999999,
"min": 0.10497759999999999,
"max": 0.19495759999999998,
"count": 10
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 2.4144848,
"min": 2.4144848,
"max": 4.2890672,
"count": 10
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00025838224000000005,
"min": 0.00025838224000000005,
"max": 0.00474838424,
"count": 10
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.005942791520000001,
"min": 0.005942791520000001,
"max": 0.10446445328000001,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 24.23715415019763,
"min": 6.491735537190083,
"max": 24.23715415019763,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 6132.0,
"min": 1571.0,
"max": 6132.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.23715415019763,
"min": 6.491735537190083,
"max": 24.23715415019763,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 6132.0,
"min": 1571.0,
"max": 6132.0,
"count": 10
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1682506138",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1682507268"
},
"total": 1129.719569039,
"count": 1,
"self": 0.8065915459997086,
"children": {
"run_training.setup": {
"total": 0.1631988450000108,
"count": 1,
"self": 0.1631988450000108
},
"TrainerController.start_learning": {
"total": 1128.749778648,
"count": 1,
"self": 1.4195873160010706,
"children": {
"TrainerController._reset_env": {
"total": 4.32628667100002,
"count": 1,
"self": 4.32628667100002
},
"TrainerController.advance": {
"total": 1122.787483321999,
"count": 45495,
"self": 0.8205928870124808,
"children": {
"env_step": {
"total": 1121.9668904349865,
"count": 45495,
"self": 788.6700607789835,
"children": {
"SubprocessEnvManager._take_step": {
"total": 332.4850570460154,
"count": 45495,
"self": 4.757049633012002,
"children": {
"TorchPolicy.evaluate": {
"total": 327.7280074130034,
"count": 45495,
"self": 327.7280074130034
}
}
},
"workers": {
"total": 0.8117726099875142,
"count": 45495,
"self": 0.0,
"children": {
"worker_root": {
"total": 1124.7430547680035,
"count": 45495,
"is_parallel": true,
"self": 479.6462137490063,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0050433369999893785,
"count": 1,
"is_parallel": true,
"self": 0.00355398099995341,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014893560000359685,
"count": 10,
"is_parallel": true,
"self": 0.0014893560000359685
}
}
},
"UnityEnvironment.step": {
"total": 0.08530069500000081,
"count": 1,
"is_parallel": true,
"self": 0.0006250640000189378,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004085120000070219,
"count": 1,
"is_parallel": true,
"self": 0.0004085120000070219
},
"communicator.exchange": {
"total": 0.0822056259999897,
"count": 1,
"is_parallel": true,
"self": 0.0822056259999897
},
"steps_from_proto": {
"total": 0.0020614929999851483,
"count": 1,
"is_parallel": true,
"self": 0.0004436069999371739,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016178860000479744,
"count": 10,
"is_parallel": true,
"self": 0.0016178860000479744
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 645.0968410189972,
"count": 45494,
"is_parallel": true,
"self": 25.578313071976368,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 14.08054805099232,
"count": 45494,
"is_parallel": true,
"self": 14.08054805099232
},
"communicator.exchange": {
"total": 521.3973878910231,
"count": 45494,
"is_parallel": true,
"self": 521.3973878910231
},
"steps_from_proto": {
"total": 84.0405920050055,
"count": 45494,
"is_parallel": true,
"self": 16.839982029972987,
"children": {
"_process_rank_one_or_two_observation": {
"total": 67.2006099750325,
"count": 454940,
"is_parallel": true,
"self": 67.2006099750325
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001463850001073297,
"count": 1,
"self": 0.0001463850001073297,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 1112.338332560025,
"count": 1212639,
"is_parallel": true,
"self": 29.810215253080287,
"children": {
"process_trajectory": {
"total": 735.4868333599446,
"count": 1212639,
"is_parallel": true,
"self": 732.5306526669444,
"children": {
"RLTrainer._checkpoint": {
"total": 2.9561806930001353,
"count": 10,
"is_parallel": true,
"self": 2.9561806930001353
}
}
},
"_update_policy": {
"total": 347.0412839470002,
"count": 227,
"is_parallel": true,
"self": 202.48499029200426,
"children": {
"TorchPPOOptimizer.update": {
"total": 144.55629365499593,
"count": 2724,
"is_parallel": true,
"self": 144.55629365499593
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.21627495400002772,
"count": 1,
"self": 0.0012642780000078346,
"children": {
"RLTrainer._checkpoint": {
"total": 0.21501067600001988,
"count": 1,
"self": 0.21501067600001988
}
}
}
}
}
}
}