Pdro-ruiz's picture
First Push
3753624 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.910011351108551,
"min": 0.8656197190284729,
"max": 2.8648324012756348,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8648.748046875,
"min": 8648.748046875,
"max": 29244.208984375,
"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": 12.425869941711426,
"min": 0.34991899132728577,
"max": 12.425869941711426,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2423.044677734375,
"min": 67.88428497314453,
"max": 2482.50537109375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06616925851823693,
"min": 0.05926711688896154,
"max": 0.07734173149672678,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26467703407294774,
"min": 0.26129032025974264,
"max": 0.3623867884840971,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19691138393154334,
"min": 0.12070066804139346,
"max": 0.29515857141391905,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7876455357261734,
"min": 0.4828026721655738,
"max": 1.4757928570695953,
"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": 24.568181818181817,
"min": 3.4318181818181817,
"max": 24.618181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1081.0,
"min": 151.0,
"max": 1354.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.568181818181817,
"min": 3.4318181818181817,
"max": 24.618181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1081.0,
"min": 151.0,
"max": 1354.0,
"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": "1740414181",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1740414603"
},
"total": 421.24864388800006,
"count": 1,
"self": 0.48575493300018024,
"children": {
"run_training.setup": {
"total": 0.022782633999895552,
"count": 1,
"self": 0.022782633999895552
},
"TrainerController.start_learning": {
"total": 420.740106321,
"count": 1,
"self": 0.3420336140151221,
"children": {
"TrainerController._reset_env": {
"total": 2.9915769550000277,
"count": 1,
"self": 2.9915769550000277
},
"TrainerController.advance": {
"total": 417.3181682669848,
"count": 18192,
"self": 0.3669360199830862,
"children": {
"env_step": {
"total": 295.2127896729975,
"count": 18192,
"self": 224.94137538300572,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.06671784899618,
"count": 18192,
"self": 1.2215718040006323,
"children": {
"TorchPolicy.evaluate": {
"total": 68.84514604499554,
"count": 18192,
"self": 68.84514604499554
}
}
},
"workers": {
"total": 0.20469644099557627,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 419.23537344600663,
"count": 18192,
"is_parallel": true,
"self": 221.76811015601197,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005878691000020808,
"count": 1,
"is_parallel": true,
"self": 0.0043751579999025125,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015035330001182956,
"count": 10,
"is_parallel": true,
"self": 0.0015035330001182956
}
}
},
"UnityEnvironment.step": {
"total": 0.03810243200007335,
"count": 1,
"is_parallel": true,
"self": 0.0005928630001790225,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003768139999920095,
"count": 1,
"is_parallel": true,
"self": 0.0003768139999920095
},
"communicator.exchange": {
"total": 0.035276182999950834,
"count": 1,
"is_parallel": true,
"self": 0.035276182999950834
},
"steps_from_proto": {
"total": 0.001856571999951484,
"count": 1,
"is_parallel": true,
"self": 0.00037617899988617864,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014803930000653054,
"count": 10,
"is_parallel": true,
"self": 0.0014803930000653054
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 197.46726328999466,
"count": 18191,
"is_parallel": true,
"self": 9.495421679997321,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.2779393760006315,
"count": 18191,
"is_parallel": true,
"self": 5.2779393760006315
},
"communicator.exchange": {
"total": 152.50354203899803,
"count": 18191,
"is_parallel": true,
"self": 152.50354203899803
},
"steps_from_proto": {
"total": 30.190360194998675,
"count": 18191,
"is_parallel": true,
"self": 5.320118532977517,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.870241662021158,
"count": 181910,
"is_parallel": true,
"self": 24.870241662021158
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 121.73844257400424,
"count": 18192,
"self": 0.41397302000052605,
"children": {
"process_trajectory": {
"total": 26.338829458004057,
"count": 18192,
"self": 25.765888316004066,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5729411419999906,
"count": 4,
"self": 0.5729411419999906
}
}
},
"_update_policy": {
"total": 94.98564009599966,
"count": 90,
"self": 37.724641506003195,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.26099858999646,
"count": 4587,
"self": 57.26099858999646
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.450000450466177e-07,
"count": 1,
"self": 8.450000450466177e-07
},
"TrainerController._save_models": {
"total": 0.08832663999999113,
"count": 1,
"self": 0.0008979300000646617,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08742870999992647,
"count": 1,
"self": 0.08742870999992647
}
}
}
}
}
}
}