Sunny98's picture
First Push
6fa0b49
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.1443512439727783,
"min": 1.1163665056228638,
"max": 2.8549373149871826,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10926.265625,
"min": 10926.265625,
"max": 29331.625,
"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": 11.952847480773926,
"min": 0.2720033824443817,
"max": 11.952847480773926,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2330.80517578125,
"min": 52.768653869628906,
"max": 2425.575927734375,
"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": 0.062240482683574,
"min": 0.05916638876314048,
"max": 0.07366866921274422,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.248961930734296,
"min": 0.23666555505256193,
"max": 0.35320865739520424,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18831872235180117,
"min": 0.12469375220711763,
"max": 0.27450502525065457,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7532748894072047,
"min": 0.49877500882847053,
"max": 1.2403962986142028,
"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": 23.59090909090909,
"min": 3.4318181818181817,
"max": 23.59090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1038.0,
"min": 151.0,
"max": 1290.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.59090909090909,
"min": 3.4318181818181817,
"max": 23.59090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1038.0,
"min": 151.0,
"max": 1290.0,
"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": "1695377930",
"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": "1695378409"
},
"total": 478.33109218899995,
"count": 1,
"self": 0.48893264599985287,
"children": {
"run_training.setup": {
"total": 0.047337921000007555,
"count": 1,
"self": 0.047337921000007555
},
"TrainerController.start_learning": {
"total": 477.7948216220001,
"count": 1,
"self": 0.5868697600006954,
"children": {
"TrainerController._reset_env": {
"total": 4.205180933999941,
"count": 1,
"self": 4.205180933999941
},
"TrainerController.advance": {
"total": 472.86803283599954,
"count": 18202,
"self": 0.29313242900275327,
"children": {
"env_step": {
"total": 472.5749004069968,
"count": 18202,
"self": 342.6029721200008,
"children": {
"SubprocessEnvManager._take_step": {
"total": 129.61673163799696,
"count": 18202,
"self": 1.9830204289989979,
"children": {
"TorchPolicy.evaluate": {
"total": 127.63371120899797,
"count": 18202,
"self": 127.63371120899797
}
}
},
"workers": {
"total": 0.35519664899902637,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 476.2484527940087,
"count": 18202,
"is_parallel": true,
"self": 223.25406024600636,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00585580500001015,
"count": 1,
"is_parallel": true,
"self": 0.004197310999984438,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001658494000025712,
"count": 10,
"is_parallel": true,
"self": 0.001658494000025712
}
}
},
"UnityEnvironment.step": {
"total": 0.050630746000024374,
"count": 1,
"is_parallel": true,
"self": 0.000689425000018673,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00032046699993770744,
"count": 1,
"is_parallel": true,
"self": 0.00032046699993770744
},
"communicator.exchange": {
"total": 0.04615632000002279,
"count": 1,
"is_parallel": true,
"self": 0.04615632000002279
},
"steps_from_proto": {
"total": 0.003464534000045205,
"count": 1,
"is_parallel": true,
"self": 0.0005662500001335502,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002898283999911655,
"count": 10,
"is_parallel": true,
"self": 0.002898283999911655
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 252.99439254800234,
"count": 18201,
"is_parallel": true,
"self": 10.71057704601401,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.383493691994204,
"count": 18201,
"is_parallel": true,
"self": 5.383493691994204
},
"communicator.exchange": {
"total": 200.41125551799234,
"count": 18201,
"is_parallel": true,
"self": 200.41125551799234
},
"steps_from_proto": {
"total": 36.48906629200178,
"count": 18201,
"is_parallel": true,
"self": 6.674833758013733,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.814232533988047,
"count": 182010,
"is_parallel": true,
"self": 29.814232533988047
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011825699994005845,
"count": 1,
"self": 0.00011825699994005845,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 469.2913758400322,
"count": 443098,
"is_parallel": true,
"self": 10.019678551072616,
"children": {
"process_trajectory": {
"total": 258.20599617996015,
"count": 443098,
"is_parallel": true,
"self": 256.6103184529603,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5956777269998383,
"count": 4,
"is_parallel": true,
"self": 1.5956777269998383
}
}
},
"_update_policy": {
"total": 201.0657011089994,
"count": 90,
"is_parallel": true,
"self": 77.1614057709985,
"children": {
"TorchPPOOptimizer.update": {
"total": 123.9042953380009,
"count": 4587,
"is_parallel": true,
"self": 123.9042953380009
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13461983499996677,
"count": 1,
"self": 0.0010079229998609662,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1336119120001058,
"count": 1,
"self": 0.1336119120001058
}
}
}
}
}
}
}