c0ldstudy's picture
First Push
6bae872
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9566054344177246,
"min": 0.9566054344177246,
"max": 2.8726820945739746,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9144.19140625,
"min": 9144.19140625,
"max": 29482.3359375,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.114566802978516,
"min": 0.35739946365356445,
"max": 13.114566802978516,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2557.340576171875,
"min": 69.33549499511719,
"max": 2666.66259765625,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06476594988157112,
"min": 0.0585379346592555,
"max": 0.0766436527775345,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2590637995262845,
"min": 0.234151738637022,
"max": 0.3832182638876725,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20295032201444402,
"min": 0.1151199469755988,
"max": 0.27682498050670995,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8118012880577761,
"min": 0.4604797879023952,
"max": 1.3841249025335498,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.863636363636363,
"min": 3.4318181818181817,
"max": 25.963636363636365,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1138.0,
"min": 151.0,
"max": 1428.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.863636363636363,
"min": 3.4318181818181817,
"max": 25.963636363636365,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1138.0,
"min": 151.0,
"max": 1428.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1680458225",
"python_version": "3.8.12 | packaged by conda-forge | (default, Sep 29 2021, 19:50:30) \n[GCC 9.4.0]",
"command_line_arguments": "/home/jason/miniconda3/envs/rl/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.0",
"numpy_version": "1.19.2",
"end_time_seconds": "1680458977"
},
"total": 751.7120985835791,
"count": 1,
"self": 0.21820257231593132,
"children": {
"run_training.setup": {
"total": 0.010598193854093552,
"count": 1,
"self": 0.010598193854093552
},
"TrainerController.start_learning": {
"total": 751.483297817409,
"count": 1,
"self": 0.35980990529060364,
"children": {
"TrainerController._reset_env": {
"total": 1.6520865745842457,
"count": 1,
"self": 1.6520865745842457
},
"TrainerController.advance": {
"total": 749.3964205160737,
"count": 18204,
"self": 0.18667157366871834,
"children": {
"env_step": {
"total": 749.209748942405,
"count": 18204,
"self": 656.8614282459021,
"children": {
"SubprocessEnvManager._take_step": {
"total": 92.17482643947005,
"count": 18204,
"self": 0.804707944393158,
"children": {
"TorchPolicy.evaluate": {
"total": 91.3701184950769,
"count": 18204,
"self": 19.95294426754117,
"children": {
"TorchPolicy.sample_actions": {
"total": 71.41717422753572,
"count": 18204,
"self": 71.41717422753572
}
}
}
}
},
"workers": {
"total": 0.17349425703287125,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 750.8852128088474,
"count": 18204,
"is_parallel": true,
"self": 142.89034443721175,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002169564366340637,
"count": 1,
"is_parallel": true,
"self": 0.0003154054284095764,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018541589379310608,
"count": 10,
"is_parallel": true,
"self": 0.0018541589379310608
}
}
},
"UnityEnvironment.step": {
"total": 0.0398939773440361,
"count": 1,
"is_parallel": true,
"self": 0.00011182203888893127,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000928681343793869,
"count": 1,
"is_parallel": true,
"self": 0.000928681343793869
},
"communicator.exchange": {
"total": 0.0369543582201004,
"count": 1,
"is_parallel": true,
"self": 0.0369543582201004
},
"steps_from_proto": {
"total": 0.0018991157412528992,
"count": 1,
"is_parallel": true,
"self": 0.00019172579050064087,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017073899507522583,
"count": 10,
"is_parallel": true,
"self": 0.0017073899507522583
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 607.9948683716357,
"count": 18203,
"is_parallel": true,
"self": 2.05359024181962,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 10.8096286021173,
"count": 18203,
"is_parallel": true,
"self": 10.8096286021173
},
"communicator.exchange": {
"total": 556.3500163145363,
"count": 18203,
"is_parallel": true,
"self": 556.3500163145363
},
"steps_from_proto": {
"total": 38.78163321316242,
"count": 18203,
"is_parallel": true,
"self": 3.599223844707012,
"children": {
"_process_rank_one_or_two_observation": {
"total": 35.18240936845541,
"count": 182030,
"is_parallel": true,
"self": 35.18240936845541
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.163228631019592e-05,
"count": 1,
"self": 8.163228631019592e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 748.8920833170414,
"count": 201892,
"is_parallel": true,
"self": 2.275763902813196,
"children": {
"process_trajectory": {
"total": 479.49006674438715,
"count": 201892,
"is_parallel": true,
"self": 478.34854831546545,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1415184289216995,
"count": 4,
"is_parallel": true,
"self": 1.1415184289216995
}
}
},
"_update_policy": {
"total": 267.12625266984105,
"count": 90,
"is_parallel": true,
"self": 37.69732262566686,
"children": {
"TorchPPOOptimizer.update": {
"total": 229.4289300441742,
"count": 4587,
"is_parallel": true,
"self": 229.4289300441742
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.07489918917417526,
"count": 1,
"self": 0.00043699145317077637,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07446219772100449,
"count": 1,
"self": 0.07446219772100449
}
}
}
}
}
}
}