AkitoP's picture
First Push
ff7baf0
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0579752922058105,
"min": 1.0579752922058105,
"max": 2.8683929443359375,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10124.8232421875,
"min": 10124.8232421875,
"max": 29375.2109375,
"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": 13.024016380310059,
"min": 0.3942826986312866,
"max": 13.024016380310059,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2539.68310546875,
"min": 76.4908447265625,
"max": 2623.352783203125,
"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": 0.06387699780216459,
"min": 0.061223764661882146,
"max": 0.07648084749291906,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25550799120865836,
"min": 0.24489505864752859,
"max": 0.36221292071080397,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19978260409598259,
"min": 0.11422986079774358,
"max": 0.30229649605119935,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7991304163839303,
"min": 0.45691944319097433,
"max": 1.4123925435192446,
"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": 25.977272727272727,
"min": 3.3863636363636362,
"max": 25.977272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1143.0,
"min": 149.0,
"max": 1416.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.977272727272727,
"min": 3.3863636363636362,
"max": 25.977272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1143.0,
"min": 149.0,
"max": 1416.0,
"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": "1691222806",
"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": "1691223325"
},
"total": 518.889396265,
"count": 1,
"self": 0.4339499819999446,
"children": {
"run_training.setup": {
"total": 0.04506219699999292,
"count": 1,
"self": 0.04506219699999292
},
"TrainerController.start_learning": {
"total": 518.410384086,
"count": 1,
"self": 0.6503216919937813,
"children": {
"TrainerController._reset_env": {
"total": 5.611185152000019,
"count": 1,
"self": 5.611185152000019
},
"TrainerController.advance": {
"total": 512.0032536880061,
"count": 18205,
"self": 0.3060536910136875,
"children": {
"env_step": {
"total": 511.6971999969924,
"count": 18205,
"self": 373.8071891489894,
"children": {
"SubprocessEnvManager._take_step": {
"total": 137.59039999200974,
"count": 18205,
"self": 2.0091766300052427,
"children": {
"TorchPolicy.evaluate": {
"total": 135.5812233620045,
"count": 18205,
"self": 135.5812233620045
}
}
},
"workers": {
"total": 0.2996108559933077,
"count": 18205,
"self": 0.0,
"children": {
"worker_root": {
"total": 516.7112248030016,
"count": 18205,
"is_parallel": true,
"self": 243.25036545100193,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0058962400000268644,
"count": 1,
"is_parallel": true,
"self": 0.004347654999889983,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015485850001368817,
"count": 10,
"is_parallel": true,
"self": 0.0015485850001368817
}
}
},
"UnityEnvironment.step": {
"total": 0.045053015999997115,
"count": 1,
"is_parallel": true,
"self": 0.0006043970000177978,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004963029999771607,
"count": 1,
"is_parallel": true,
"self": 0.0004963029999771607
},
"communicator.exchange": {
"total": 0.041538320000029216,
"count": 1,
"is_parallel": true,
"self": 0.041538320000029216
},
"steps_from_proto": {
"total": 0.00241399599997294,
"count": 1,
"is_parallel": true,
"self": 0.00046746999987590243,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019465260000970375,
"count": 10,
"is_parallel": true,
"self": 0.0019465260000970375
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 273.4608593519997,
"count": 18204,
"is_parallel": true,
"self": 11.251894527006698,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.924270179000587,
"count": 18204,
"is_parallel": true,
"self": 5.924270179000587
},
"communicator.exchange": {
"total": 215.47043369999665,
"count": 18204,
"is_parallel": true,
"self": 215.47043369999665
},
"steps_from_proto": {
"total": 40.814260945995784,
"count": 18204,
"is_parallel": true,
"self": 7.494441891961628,
"children": {
"_process_rank_one_or_two_observation": {
"total": 33.319819054034156,
"count": 182040,
"is_parallel": true,
"self": 33.319819054034156
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00017230000003110035,
"count": 1,
"self": 0.00017230000003110035,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 507.70970544804254,
"count": 475407,
"is_parallel": true,
"self": 11.75518956110028,
"children": {
"process_trajectory": {
"total": 279.52979876994254,
"count": 475407,
"is_parallel": true,
"self": 277.7316337519426,
"children": {
"RLTrainer._checkpoint": {
"total": 1.7981650179999633,
"count": 4,
"is_parallel": true,
"self": 1.7981650179999633
}
}
},
"_update_policy": {
"total": 216.42471711699972,
"count": 90,
"is_parallel": true,
"self": 86.58008902399422,
"children": {
"TorchPPOOptimizer.update": {
"total": 129.8446280930055,
"count": 4587,
"is_parallel": true,
"self": 129.8446280930055
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14545125400002235,
"count": 1,
"self": 0.0008987279999246311,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14455252600009771,
"count": 1,
"self": 0.14455252600009771
}
}
}
}
}
}
}