joshuaoreilly's picture
First Push
c00072f
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8196663856506348,
"min": 0.818583071231842,
"max": 2.869926691055298,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7862.240234375,
"min": 7862.240234375,
"max": 29485.626953125,
"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": 12.98060131072998,
"min": 0.42844271659851074,
"max": 12.98060131072998,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2531.21728515625,
"min": 83.11788940429688,
"max": 2632.205322265625,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06900985194585577,
"min": 0.0643883801200062,
"max": 0.0758808064023398,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27603940778342306,
"min": 0.2575535204800248,
"max": 0.3669302324304841,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20340050866498666,
"min": 0.1222658503330404,
"max": 0.2673981816453092,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8136020346599466,
"min": 0.4890634013321616,
"max": 1.2766954454721189,
"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": 25.113636363636363,
"min": 3.477272727272727,
"max": 26.054545454545455,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1105.0,
"min": 153.0,
"max": 1433.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.113636363636363,
"min": 3.477272727272727,
"max": 26.054545454545455,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1105.0,
"min": 153.0,
"max": 1433.0,
"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": "1699316264",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"command_line_arguments": "/home/joshua/.unit5env/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1699316495"
},
"total": 230.76326891400095,
"count": 1,
"self": 0.2184263630042551,
"children": {
"run_training.setup": {
"total": 0.0333535829995526,
"count": 1,
"self": 0.0333535829995526
},
"TrainerController.start_learning": {
"total": 230.51148896799714,
"count": 1,
"self": 0.34229900750506204,
"children": {
"TrainerController._reset_env": {
"total": 0.6590862929879222,
"count": 1,
"self": 0.6590862929879222
},
"TrainerController.advance": {
"total": 229.4585794105078,
"count": 18203,
"self": 0.17267339561658446,
"children": {
"env_step": {
"total": 229.28590601489122,
"count": 18203,
"self": 147.92553472463624,
"children": {
"SubprocessEnvManager._take_step": {
"total": 81.1833726377372,
"count": 18203,
"self": 0.8135388882074039,
"children": {
"TorchPolicy.evaluate": {
"total": 80.36983374952979,
"count": 18203,
"self": 80.36983374952979
}
}
},
"workers": {
"total": 0.17699865251779556,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 230.13103304512333,
"count": 18203,
"is_parallel": true,
"self": 128.79174137355585,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010211409971816465,
"count": 1,
"is_parallel": true,
"self": 0.000306301997625269,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007148389995563775,
"count": 10,
"is_parallel": true,
"self": 0.0007148389995563775
}
}
},
"UnityEnvironment.step": {
"total": 0.015202560010948218,
"count": 1,
"is_parallel": true,
"self": 0.00021464900055434555,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001620130060473457,
"count": 1,
"is_parallel": true,
"self": 0.0001620130060473457
},
"communicator.exchange": {
"total": 0.014094387006480247,
"count": 1,
"is_parallel": true,
"self": 0.014094387006480247
},
"steps_from_proto": {
"total": 0.0007315109978662804,
"count": 1,
"is_parallel": true,
"self": 0.00017749598191585392,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005540150159504265,
"count": 10,
"is_parallel": true,
"self": 0.0005540150159504265
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 101.33929167156748,
"count": 18202,
"is_parallel": true,
"self": 4.312789620977128,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.5528869192348793,
"count": 18202,
"is_parallel": true,
"self": 2.5528869192348793
},
"communicator.exchange": {
"total": 80.49925705861824,
"count": 18202,
"is_parallel": true,
"self": 80.49925705861824
},
"steps_from_proto": {
"total": 13.974358072737232,
"count": 18202,
"is_parallel": true,
"self": 2.987792225118028,
"children": {
"_process_rank_one_or_two_observation": {
"total": 10.986565847619204,
"count": 182020,
"is_parallel": true,
"self": 10.986565847619204
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.174999675247818e-05,
"count": 1,
"self": 8.174999675247818e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 229.19039315739064,
"count": 168937,
"is_parallel": true,
"self": 1.5284366427658824,
"children": {
"process_trajectory": {
"total": 126.19110758371244,
"count": 168937,
"is_parallel": true,
"self": 125.88199940470804,
"children": {
"RLTrainer._checkpoint": {
"total": 0.30910817900439724,
"count": 4,
"is_parallel": true,
"self": 0.30910817900439724
}
}
},
"_update_policy": {
"total": 101.47084893091233,
"count": 90,
"is_parallel": true,
"self": 24.680153356297524,
"children": {
"TorchPPOOptimizer.update": {
"total": 76.7906955746148,
"count": 4587,
"is_parallel": true,
"self": 76.7906955746148
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.0514425069995923,
"count": 1,
"self": 0.0005083129944978282,
"children": {
"RLTrainer._checkpoint": {
"total": 0.05093419400509447,
"count": 1,
"self": 0.05093419400509447
}
}
}
}
}
}
}