byfengwu's picture
First Push
7de1389 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7438400983810425,
"min": 0.7438400983810425,
"max": 2.8733410835266113,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7069.4560546875,
"min": 7069.4560546875,
"max": 29331.06640625,
"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": 13.24613094329834,
"min": 0.24109481275081635,
"max": 13.24613094329834,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2582.99560546875,
"min": 46.77239227294922,
"max": 2676.44091796875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06702861777596934,
"min": 0.060474072044170865,
"max": 0.0776448083744767,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26811447110387737,
"min": 0.24189628817668346,
"max": 0.35168024477338894,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18499002335410492,
"min": 0.09303034640570154,
"max": 0.31261131627594724,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7399600934164197,
"min": 0.37212138562280617,
"max": 1.4345333082418814,
"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": 26.363636363636363,
"min": 2.772727272727273,
"max": 26.363636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1160.0,
"min": 122.0,
"max": 1415.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.363636363636363,
"min": 2.772727272727273,
"max": 26.363636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1160.0,
"min": 122.0,
"max": 1415.0,
"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": "1778026284",
"python_version": "3.10.10 (main, Mar 21 2023, 18:45:11) [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": "1778026709"
},
"total": 424.70969311800036,
"count": 1,
"self": 0.4870298379992164,
"children": {
"run_training.setup": {
"total": 0.03693676800139656,
"count": 1,
"self": 0.03693676800139656
},
"TrainerController.start_learning": {
"total": 424.18572651199975,
"count": 1,
"self": 0.32001042095726007,
"children": {
"TrainerController._reset_env": {
"total": 3.6275336790004076,
"count": 1,
"self": 3.6275336790004076
},
"TrainerController.advance": {
"total": 420.1622600130413,
"count": 18192,
"self": 0.3437884602080885,
"children": {
"env_step": {
"total": 301.45370267887483,
"count": 18192,
"self": 233.7449986947322,
"children": {
"SubprocessEnvManager._take_step": {
"total": 67.49978193914467,
"count": 18192,
"self": 1.2176911552996899,
"children": {
"TorchPolicy.evaluate": {
"total": 66.28209078384498,
"count": 18192,
"self": 66.28209078384498
}
}
},
"workers": {
"total": 0.20892204499796208,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 422.140192097977,
"count": 18192,
"is_parallel": true,
"self": 216.71242000511666,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0073125069993693614,
"count": 1,
"is_parallel": true,
"self": 0.0034853069992095698,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0038272000001597917,
"count": 10,
"is_parallel": true,
"self": 0.0038272000001597917
}
}
},
"UnityEnvironment.step": {
"total": 0.03432429900021816,
"count": 1,
"is_parallel": true,
"self": 0.0005580610013566911,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003764529992622556,
"count": 1,
"is_parallel": true,
"self": 0.0003764529992622556
},
"communicator.exchange": {
"total": 0.031537371998638264,
"count": 1,
"is_parallel": true,
"self": 0.031537371998638264
},
"steps_from_proto": {
"total": 0.0018524130009609507,
"count": 1,
"is_parallel": true,
"self": 0.0003461500018602237,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001506262999100727,
"count": 10,
"is_parallel": true,
"self": 0.001506262999100727
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 205.42777209286032,
"count": 18191,
"is_parallel": true,
"self": 9.813661843580121,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.155280595161457,
"count": 18191,
"is_parallel": true,
"self": 5.155280595161457
},
"communicator.exchange": {
"total": 156.26171780396726,
"count": 18191,
"is_parallel": true,
"self": 156.26171780396726
},
"steps_from_proto": {
"total": 34.19711185015149,
"count": 18191,
"is_parallel": true,
"self": 6.169904553578817,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.02720729657267,
"count": 181910,
"is_parallel": true,
"self": 28.02720729657267
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 118.36476887395838,
"count": 18192,
"self": 0.4000581938198593,
"children": {
"process_trajectory": {
"total": 26.32711353114246,
"count": 18192,
"self": 25.943540612141078,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3835729190013808,
"count": 4,
"self": 0.3835729190013808
}
}
},
"_update_policy": {
"total": 91.63759714899606,
"count": 90,
"self": 36.919012084015776,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.71858506498029,
"count": 4587,
"self": 54.71858506498029
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.070008673006669e-07,
"count": 1,
"self": 9.070008673006669e-07
},
"TrainerController._save_models": {
"total": 0.07592149199990672,
"count": 1,
"self": 0.0007129159985197475,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07520857600138697,
"count": 1,
"self": 0.07520857600138697
}
}
}
}
}
}
}