SjcCss's picture
First Push
a2f4df8 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8905637860298157,
"min": 0.8905637860298157,
"max": 2.8610036373138428,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8463.91796875,
"min": 8463.91796875,
"max": 29205.125,
"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": 13.207624435424805,
"min": 0.3360954225063324,
"max": 13.207624435424805,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2575.48681640625,
"min": 65.2025146484375,
"max": 2676.772705078125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07786139157328495,
"min": 0.06163916161161729,
"max": 0.07786139157328495,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3114455662931398,
"min": 0.2474892920410425,
"max": 0.3787693647021774,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19046888310535282,
"min": 0.1284061935741692,
"max": 0.29051362810765996,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7618755324214113,
"min": 0.5136247742966767,
"max": 1.3917784088966894,
"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.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.Environment.CumulativeReward.mean": {
"value": 26.09090909090909,
"min": 3.3181818181818183,
"max": 26.09090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1148.0,
"min": 146.0,
"max": 1420.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.09090909090909,
"min": 3.3181818181818183,
"max": 26.09090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1148.0,
"min": 146.0,
"max": 1420.0,
"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": "1758109272",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1758109787"
},
"total": 514.4904061990001,
"count": 1,
"self": 0.4436898989997644,
"children": {
"run_training.setup": {
"total": 0.026569523000034678,
"count": 1,
"self": 0.026569523000034678
},
"TrainerController.start_learning": {
"total": 514.0201467770003,
"count": 1,
"self": 0.5254159270032233,
"children": {
"TrainerController._reset_env": {
"total": 2.966568522000216,
"count": 1,
"self": 2.966568522000216
},
"TrainerController.advance": {
"total": 510.4369315659967,
"count": 18192,
"self": 0.5486707500349439,
"children": {
"env_step": {
"total": 377.3691673819915,
"count": 18192,
"self": 289.59584461297777,
"children": {
"SubprocessEnvManager._take_step": {
"total": 87.44154385901356,
"count": 18192,
"self": 1.704052673022943,
"children": {
"TorchPolicy.evaluate": {
"total": 85.73749118599062,
"count": 18192,
"self": 85.73749118599062
}
}
},
"workers": {
"total": 0.33177891000013915,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 512.0991981620066,
"count": 18192,
"is_parallel": true,
"self": 261.00244316299904,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00500556800011509,
"count": 1,
"is_parallel": true,
"self": 0.003498648000004323,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015069200001107674,
"count": 10,
"is_parallel": true,
"self": 0.0015069200001107674
}
}
},
"UnityEnvironment.step": {
"total": 0.03877215600005002,
"count": 1,
"is_parallel": true,
"self": 0.0006041010001354152,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004483340001115721,
"count": 1,
"is_parallel": true,
"self": 0.0004483340001115721
},
"communicator.exchange": {
"total": 0.03559477599992533,
"count": 1,
"is_parallel": true,
"self": 0.03559477599992533
},
"steps_from_proto": {
"total": 0.002124944999877698,
"count": 1,
"is_parallel": true,
"self": 0.00041939799962165125,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017055470002560469,
"count": 10,
"is_parallel": true,
"self": 0.0017055470002560469
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 251.09675499900754,
"count": 18191,
"is_parallel": true,
"self": 11.35262030800709,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.5562993920082135,
"count": 18191,
"is_parallel": true,
"self": 6.5562993920082135
},
"communicator.exchange": {
"total": 196.04087448999758,
"count": 18191,
"is_parallel": true,
"self": 196.04087448999758
},
"steps_from_proto": {
"total": 37.14696080899466,
"count": 18191,
"is_parallel": true,
"self": 7.030755005028595,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.116205803966068,
"count": 181910,
"is_parallel": true,
"self": 30.116205803966068
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 132.51909343397028,
"count": 18192,
"self": 0.6838876749704923,
"children": {
"process_trajectory": {
"total": 30.40836274800131,
"count": 18192,
"self": 29.95113625100157,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4572264969997377,
"count": 4,
"self": 0.4572264969997377
}
}
},
"_update_policy": {
"total": 101.42684301099848,
"count": 90,
"self": 40.17844289599702,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.24840011500146,
"count": 4587,
"self": 61.24840011500146
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1070001164625864e-06,
"count": 1,
"self": 1.1070001164625864e-06
},
"TrainerController._save_models": {
"total": 0.09122965500000646,
"count": 1,
"self": 0.0010282450002705446,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09020140999973592,
"count": 1,
"self": 0.09020140999973592
}
}
}
}
}
}
}