iamjoy's picture
First Push
cd845f2
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9283290505409241,
"min": 0.9101920127868652,
"max": 2.871617555618286,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8873.8974609375,
"min": 8873.8974609375,
"max": 29408.236328125,
"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": 12.916648864746094,
"min": 0.35144364833831787,
"max": 12.916648864746094,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2518.74658203125,
"min": 68.18006896972656,
"max": 2613.5908203125,
"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": 0.06555301947696089,
"min": 0.0640257782851775,
"max": 0.07485714870220844,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26221207790784357,
"min": 0.25610311314071,
"max": 0.3742857435110422,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19812303803422873,
"min": 0.10419536082932325,
"max": 0.2915158127452813,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7924921521369149,
"min": 0.416781443317293,
"max": 1.4575790637264066,
"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": 25.681818181818183,
"min": 3.022727272727273,
"max": 25.836363636363636,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1130.0,
"min": 133.0,
"max": 1421.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.681818181818183,
"min": 3.022727272727273,
"max": 25.836363636363636,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1130.0,
"min": 133.0,
"max": 1421.0,
"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": "1683884583",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
"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": "1683885044"
},
"total": 461.39500813199993,
"count": 1,
"self": 0.43747293399997034,
"children": {
"run_training.setup": {
"total": 0.0451964979999957,
"count": 1,
"self": 0.0451964979999957
},
"TrainerController.start_learning": {
"total": 460.91233869999996,
"count": 1,
"self": 0.5610013849950519,
"children": {
"TrainerController._reset_env": {
"total": 4.398666848999937,
"count": 1,
"self": 4.398666848999937
},
"TrainerController.advance": {
"total": 455.8174324450049,
"count": 18202,
"self": 0.2585295309977482,
"children": {
"env_step": {
"total": 455.55890291400715,
"count": 18202,
"self": 336.22769647997916,
"children": {
"SubprocessEnvManager._take_step": {
"total": 119.06589548299621,
"count": 18202,
"self": 1.6987648540045939,
"children": {
"TorchPolicy.evaluate": {
"total": 117.36713062899162,
"count": 18202,
"self": 117.36713062899162
}
}
},
"workers": {
"total": 0.26531095103177904,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 459.38248301701196,
"count": 18202,
"is_parallel": true,
"self": 214.06549185801168,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005357363999792142,
"count": 1,
"is_parallel": true,
"self": 0.0039955479999207455,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013618159998713963,
"count": 10,
"is_parallel": true,
"self": 0.0013618159998713963
}
}
},
"UnityEnvironment.step": {
"total": 0.10681338499989579,
"count": 1,
"is_parallel": true,
"self": 0.0006323699999484234,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00035924600001635554,
"count": 1,
"is_parallel": true,
"self": 0.00035924600001635554
},
"communicator.exchange": {
"total": 0.10380546999999751,
"count": 1,
"is_parallel": true,
"self": 0.10380546999999751
},
"steps_from_proto": {
"total": 0.002016298999933497,
"count": 1,
"is_parallel": true,
"self": 0.0005129549997491267,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00150334400018437,
"count": 10,
"is_parallel": true,
"self": 0.00150334400018437
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 245.31699115900028,
"count": 18201,
"is_parallel": true,
"self": 9.473126969993018,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.092255837010725,
"count": 18201,
"is_parallel": true,
"self": 5.092255837010725
},
"communicator.exchange": {
"total": 198.73783469100454,
"count": 18201,
"is_parallel": true,
"self": 198.73783469100454
},
"steps_from_proto": {
"total": 32.013773660992,
"count": 18201,
"is_parallel": true,
"self": 6.079683952909363,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.934089708082638,
"count": 182010,
"is_parallel": true,
"self": 25.934089708082638
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011723200009328139,
"count": 1,
"self": 0.00011723200009328139,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 452.5209283770341,
"count": 405890,
"is_parallel": true,
"self": 9.044535370838503,
"children": {
"process_trajectory": {
"total": 247.5801325191951,
"count": 405890,
"is_parallel": true,
"self": 246.84118204019524,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7389504789998682,
"count": 4,
"is_parallel": true,
"self": 0.7389504789998682
}
}
},
"_update_policy": {
"total": 195.89626048700052,
"count": 90,
"is_parallel": true,
"self": 77.06506854399936,
"children": {
"TorchPPOOptimizer.update": {
"total": 118.83119194300116,
"count": 4587,
"is_parallel": true,
"self": 118.83119194300116
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13512078899998414,
"count": 1,
"self": 0.0009046069999385509,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1342161820000456,
"count": 1,
"self": 0.1342161820000456
}
}
}
}
}
}
}