BrianLan's picture
First Push
6de7dac verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7903927564620972,
"min": 0.7903927564620972,
"max": 2.844977855682373,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7511.892578125,
"min": 7511.892578125,
"max": 29041.533203125,
"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": 12.862939834594727,
"min": 0.38439831137657166,
"max": 12.862939834594727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2508.273193359375,
"min": 74.57327270507812,
"max": 2601.552490234375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07157898143130154,
"min": 0.06313106732502725,
"max": 0.07604620969356676,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28631592572520614,
"min": 0.252524269300109,
"max": 0.38023104846783384,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18271786639211224,
"min": 0.1314613158670802,
"max": 0.3233489774605808,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.730871465568449,
"min": 0.5258452634683208,
"max": 1.6167448873029038,
"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": 25.318181818181817,
"min": 3.9318181818181817,
"max": 25.454545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1114.0,
"min": 173.0,
"max": 1400.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.318181818181817,
"min": 3.9318181818181817,
"max": 25.454545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1114.0,
"min": 173.0,
"max": 1400.0,
"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": "1749118336",
"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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1749118783"
},
"total": 447.6101253759999,
"count": 1,
"self": 0.4379972319999865,
"children": {
"run_training.setup": {
"total": 0.023108126000010998,
"count": 1,
"self": 0.023108126000010998
},
"TrainerController.start_learning": {
"total": 447.14902001799993,
"count": 1,
"self": 0.3795735020002553,
"children": {
"TrainerController._reset_env": {
"total": 3.3146786610000163,
"count": 1,
"self": 3.3146786610000163
},
"TrainerController.advance": {
"total": 443.3665157099997,
"count": 18192,
"self": 0.41650583399257357,
"children": {
"env_step": {
"total": 317.1048864630034,
"count": 18192,
"self": 241.95289290999324,
"children": {
"SubprocessEnvManager._take_step": {
"total": 74.92484081100883,
"count": 18192,
"self": 1.3325374120151992,
"children": {
"TorchPolicy.evaluate": {
"total": 73.59230339899364,
"count": 18192,
"self": 73.59230339899364
}
}
},
"workers": {
"total": 0.22715274200135127,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 445.6740082729903,
"count": 18192,
"is_parallel": true,
"self": 234.07234906298459,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0057726100000081715,
"count": 1,
"is_parallel": true,
"self": 0.004221838999967531,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015507710000406405,
"count": 10,
"is_parallel": true,
"self": 0.0015507710000406405
}
}
},
"UnityEnvironment.step": {
"total": 0.07409704999997757,
"count": 1,
"is_parallel": true,
"self": 0.0005654369999774644,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004043220000085057,
"count": 1,
"is_parallel": true,
"self": 0.0004043220000085057
},
"communicator.exchange": {
"total": 0.07135216500000752,
"count": 1,
"is_parallel": true,
"self": 0.07135216500000752
},
"steps_from_proto": {
"total": 0.001775125999984084,
"count": 1,
"is_parallel": true,
"self": 0.00033829200003765436,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014368339999464297,
"count": 10,
"is_parallel": true,
"self": 0.0014368339999464297
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 211.60165921000572,
"count": 18191,
"is_parallel": true,
"self": 10.081067075004341,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.616670897011147,
"count": 18191,
"is_parallel": true,
"self": 5.616670897011147
},
"communicator.exchange": {
"total": 162.8056305679948,
"count": 18191,
"is_parallel": true,
"self": 162.8056305679948
},
"steps_from_proto": {
"total": 33.098290669995436,
"count": 18191,
"is_parallel": true,
"self": 5.968540465959222,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.129750204036213,
"count": 181910,
"is_parallel": true,
"self": 27.129750204036213
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 125.8451234130037,
"count": 18192,
"self": 0.4723545529952844,
"children": {
"process_trajectory": {
"total": 28.55903657100788,
"count": 18192,
"self": 28.13877492400792,
"children": {
"RLTrainer._checkpoint": {
"total": 0.42026164699996116,
"count": 4,
"self": 0.42026164699996116
}
}
},
"_update_policy": {
"total": 96.81373228900054,
"count": 90,
"self": 39.99186372300085,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.821868565999694,
"count": 4587,
"self": 56.821868565999694
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.289999525208259e-07,
"count": 1,
"self": 9.289999525208259e-07
},
"TrainerController._save_models": {
"total": 0.0882512160000033,
"count": 1,
"self": 0.0008836270000074364,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08736758899999586,
"count": 1,
"self": 0.08736758899999586
}
}
}
}
}
}
}