InexperiencedMe's picture
First Push
6c6eef2
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8394624590873718,
"min": 0.8394624590873718,
"max": 2.8724913597106934,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8015.1875,
"min": 8015.1875,
"max": 29480.37890625,
"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": 12.999176025390625,
"min": 0.31306368112564087,
"max": 12.999176025390625,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2534.83935546875,
"min": 60.734352111816406,
"max": 2636.59619140625,
"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": 0.07152800359614832,
"min": 0.06076592602752784,
"max": 0.07334848210488346,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28611201438459327,
"min": 0.26803841098872533,
"max": 0.3667424105244173,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21237558352888797,
"min": 0.11702865158440545,
"max": 0.2836712506033626,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8495023341155519,
"min": 0.4681146063376218,
"max": 1.3625467890033536,
"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": 25.477272727272727,
"min": 2.8636363636363638,
"max": 25.581818181818182,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1121.0,
"min": 126.0,
"max": 1407.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.477272727272727,
"min": 2.8636363636363638,
"max": 25.581818181818182,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1121.0,
"min": 126.0,
"max": 1407.0,
"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": "1694803144",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"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": "1694803622"
},
"total": 478.27751010500015,
"count": 1,
"self": 0.44239849100017636,
"children": {
"run_training.setup": {
"total": 0.04277341500005605,
"count": 1,
"self": 0.04277341500005605
},
"TrainerController.start_learning": {
"total": 477.7923381989999,
"count": 1,
"self": 0.5895605639950645,
"children": {
"TrainerController._reset_env": {
"total": 4.246030464999876,
"count": 1,
"self": 4.246030464999876
},
"TrainerController.advance": {
"total": 472.8071249990053,
"count": 18201,
"self": 0.29143334599712034,
"children": {
"env_step": {
"total": 472.51569165300816,
"count": 18201,
"self": 344.48659121403057,
"children": {
"SubprocessEnvManager._take_step": {
"total": 127.71940610599222,
"count": 18201,
"self": 1.8302605459934966,
"children": {
"TorchPolicy.evaluate": {
"total": 125.88914555999872,
"count": 18201,
"self": 125.88914555999872
}
}
},
"workers": {
"total": 0.30969433298537297,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 476.0096707000175,
"count": 18201,
"is_parallel": true,
"self": 220.96212809900817,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005765479999809031,
"count": 1,
"is_parallel": true,
"self": 0.0042501509999510745,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015153289998579567,
"count": 10,
"is_parallel": true,
"self": 0.0015153289998579567
}
}
},
"UnityEnvironment.step": {
"total": 0.04013665699994817,
"count": 1,
"is_parallel": true,
"self": 0.0006993550000515825,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00035591300002124626,
"count": 1,
"is_parallel": true,
"self": 0.00035591300002124626
},
"communicator.exchange": {
"total": 0.03604701299991575,
"count": 1,
"is_parallel": true,
"self": 0.03604701299991575
},
"steps_from_proto": {
"total": 0.003034375999959593,
"count": 1,
"is_parallel": true,
"self": 0.00038010499974916456,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0026542710002104286,
"count": 10,
"is_parallel": true,
"self": 0.0026542710002104286
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 255.04754260100935,
"count": 18200,
"is_parallel": true,
"self": 10.85938967800962,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.449080781992734,
"count": 18200,
"is_parallel": true,
"self": 5.449080781992734
},
"communicator.exchange": {
"total": 202.6476512800018,
"count": 18200,
"is_parallel": true,
"self": 202.6476512800018
},
"steps_from_proto": {
"total": 36.09142086100519,
"count": 18200,
"is_parallel": true,
"self": 6.690874288025725,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.400546572979465,
"count": 182000,
"is_parallel": true,
"self": 29.400546572979465
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013071499984107504,
"count": 1,
"self": 0.00013071499984107504,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 469.2696991720238,
"count": 448276,
"is_parallel": true,
"self": 9.705767601029265,
"children": {
"process_trajectory": {
"total": 258.03542908799386,
"count": 448276,
"is_parallel": true,
"self": 257.22235389599405,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8130751919998147,
"count": 4,
"is_parallel": true,
"self": 0.8130751919998147
}
}
},
"_update_policy": {
"total": 201.5285024830007,
"count": 90,
"is_parallel": true,
"self": 76.42902271099365,
"children": {
"TorchPPOOptimizer.update": {
"total": 125.09947977200704,
"count": 4587,
"is_parallel": true,
"self": 125.09947977200704
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1494914559998506,
"count": 1,
"self": 0.000917315999913626,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14857413999993696,
"count": 1,
"self": 0.14857413999993696
}
}
}
}
}
}
}