qddwudan's picture
First Push
7ab7653
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0988280773162842,
"min": 1.096425175666809,
"max": 2.8573222160339355,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10491.6103515625,
"min": 10491.6103515625,
"max": 29293.267578125,
"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": 12.142365455627441,
"min": 0.2833123207092285,
"max": 12.142365455627441,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2367.76123046875,
"min": 54.962589263916016,
"max": 2437.8681640625,
"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": 0.07548239480363954,
"min": 0.06390212022604685,
"max": 0.07548239480363954,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.30192957921455815,
"min": 0.2556084809041874,
"max": 0.3611073440041247,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.23292841652736945,
"min": 0.08791373244043914,
"max": 0.2890616550165064,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9317136661094778,
"min": 0.35165492976175655,
"max": 1.3428292590029098,
"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": 24.454545454545453,
"min": 2.6363636363636362,
"max": 24.454545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1076.0,
"min": 116.0,
"max": 1319.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.454545454545453,
"min": 2.6363636363636362,
"max": 24.454545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1076.0,
"min": 116.0,
"max": 1319.0,
"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": "1691760325",
"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": "1691760790"
},
"total": 465.66347961299994,
"count": 1,
"self": 0.3942072779999535,
"children": {
"run_training.setup": {
"total": 0.042414716999928714,
"count": 1,
"self": 0.042414716999928714
},
"TrainerController.start_learning": {
"total": 465.22685761800005,
"count": 1,
"self": 0.5342237589973138,
"children": {
"TrainerController._reset_env": {
"total": 4.135704164000003,
"count": 1,
"self": 4.135704164000003
},
"TrainerController.advance": {
"total": 460.4092274290026,
"count": 18200,
"self": 0.26427132799324227,
"children": {
"env_step": {
"total": 460.14495610100937,
"count": 18200,
"self": 335.2639191069941,
"children": {
"SubprocessEnvManager._take_step": {
"total": 124.61190512001235,
"count": 18200,
"self": 1.6943130109995082,
"children": {
"TorchPolicy.evaluate": {
"total": 122.91759210901284,
"count": 18200,
"self": 122.91759210901284
}
}
},
"workers": {
"total": 0.26913187400293737,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 463.50046097198606,
"count": 18200,
"is_parallel": true,
"self": 222.18982700496747,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005412823000028766,
"count": 1,
"is_parallel": true,
"self": 0.003925626000068405,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014871969999603607,
"count": 10,
"is_parallel": true,
"self": 0.0014871969999603607
}
}
},
"UnityEnvironment.step": {
"total": 0.03521664200002306,
"count": 1,
"is_parallel": true,
"self": 0.0006097259999933158,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003239259999645583,
"count": 1,
"is_parallel": true,
"self": 0.0003239259999645583
},
"communicator.exchange": {
"total": 0.032089845000086825,
"count": 1,
"is_parallel": true,
"self": 0.032089845000086825
},
"steps_from_proto": {
"total": 0.002193144999978358,
"count": 1,
"is_parallel": true,
"self": 0.00039066299996193266,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018024820000164254,
"count": 10,
"is_parallel": true,
"self": 0.0018024820000164254
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 241.3106339670186,
"count": 18199,
"is_parallel": true,
"self": 10.45933148003769,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.174951845991586,
"count": 18199,
"is_parallel": true,
"self": 5.174951845991586
},
"communicator.exchange": {
"total": 190.55214120899188,
"count": 18199,
"is_parallel": true,
"self": 190.55214120899188
},
"steps_from_proto": {
"total": 35.12420943199743,
"count": 18199,
"is_parallel": true,
"self": 6.3115663189986435,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.812643112998785,
"count": 181990,
"is_parallel": true,
"self": 28.812643112998785
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00010957600011352042,
"count": 1,
"self": 0.00010957600011352042,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 456.8354167299807,
"count": 422659,
"is_parallel": true,
"self": 9.638143035956091,
"children": {
"process_trajectory": {
"total": 247.76211590302455,
"count": 422659,
"is_parallel": true,
"self": 246.98096063802473,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7811552649998248,
"count": 4,
"is_parallel": true,
"self": 0.7811552649998248
}
}
},
"_update_policy": {
"total": 199.43515779100005,
"count": 90,
"is_parallel": true,
"self": 81.26550780501123,
"children": {
"TorchPPOOptimizer.update": {
"total": 118.16964998598883,
"count": 4587,
"is_parallel": true,
"self": 118.16964998598883
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1475926900000104,
"count": 1,
"self": 0.0009609660000933218,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14663172399991709,
"count": 1,
"self": 0.14663172399991709
}
}
}
}
}
}
}