ppo-Huggy / run_logs /timers.json
aviroes's picture
Huggy
5e45c97
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4049434661865234,
"min": 1.4049434661865234,
"max": 1.4265085458755493,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70970.71875,
"min": 68662.75,
"max": 78175.484375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 70.94049346879535,
"min": 69.26966292134831,
"max": 383.31297709923666,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 48878.0,
"min": 48878.0,
"max": 50214.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999928.0,
"min": 49902.0,
"max": 1999928.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999928.0,
"min": 49902.0,
"max": 1999928.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.448381185531616,
"min": 0.10617030411958694,
"max": 2.525758743286133,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1686.9345703125,
"min": 13.802139282226562,
"max": 1775.6298828125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.78198886523226,
"min": 1.6748552542466384,
"max": 4.061697514898026,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2605.790328145027,
"min": 217.731183052063,
"max": 2816.1964033842087,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.78198886523226,
"min": 1.6748552542466384,
"max": 4.061697514898026,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2605.790328145027,
"min": 217.731183052063,
"max": 2816.1964033842087,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017198521902577747,
"min": 0.01406178480028757,
"max": 0.01887106258946005,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.051595565707733236,
"min": 0.02812356960057514,
"max": 0.05565141196517895,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05684647924370236,
"min": 0.021991277144600946,
"max": 0.06035287868645456,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17053943773110708,
"min": 0.04398255428920189,
"max": 0.18105863605936368,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.7774987408666747e-06,
"min": 3.7774987408666747e-06,
"max": 0.00029526022657992495,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1332496222600024e-05,
"min": 1.1332496222600024e-05,
"max": 0.00084365896878035,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10125913333333335,
"min": 0.10125913333333335,
"max": 0.19842007500000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30377740000000003,
"min": 0.20765195000000006,
"max": 0.5812196500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.283075333333346e-05,
"min": 7.283075333333346e-05,
"max": 0.0049211617425,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002184922600000004,
"min": 0.0002184922600000004,
"max": 0.014062860534999997,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1700427477",
"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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1700429956"
},
"total": 2479.757458498,
"count": 1,
"self": 0.4821852909994959,
"children": {
"run_training.setup": {
"total": 0.04667795200001024,
"count": 1,
"self": 0.04667795200001024
},
"TrainerController.start_learning": {
"total": 2479.228595255,
"count": 1,
"self": 4.603059771051903,
"children": {
"TrainerController._reset_env": {
"total": 10.076321726000003,
"count": 1,
"self": 10.076321726000003
},
"TrainerController.advance": {
"total": 2464.4487736229485,
"count": 233791,
"self": 4.700652241873286,
"children": {
"env_step": {
"total": 1941.3383304670815,
"count": 233791,
"self": 1602.9474554071094,
"children": {
"SubprocessEnvManager._take_step": {
"total": 335.46219863698843,
"count": 233791,
"self": 16.806866278939992,
"children": {
"TorchPolicy.evaluate": {
"total": 318.65533235804844,
"count": 223011,
"self": 318.65533235804844
}
}
},
"workers": {
"total": 2.928676422983841,
"count": 233791,
"self": 0.0,
"children": {
"worker_root": {
"total": 2471.6148268029965,
"count": 233791,
"is_parallel": true,
"self": 1163.7949316180493,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009307120000130453,
"count": 1,
"is_parallel": true,
"self": 0.00026207800001998294,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006686339999930624,
"count": 2,
"is_parallel": true,
"self": 0.0006686339999930624
}
}
},
"UnityEnvironment.step": {
"total": 0.029784274000007827,
"count": 1,
"is_parallel": true,
"self": 0.00034877100003427586,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020521599998346574,
"count": 1,
"is_parallel": true,
"self": 0.00020521599998346574
},
"communicator.exchange": {
"total": 0.028501382999991165,
"count": 1,
"is_parallel": true,
"self": 0.028501382999991165
},
"steps_from_proto": {
"total": 0.00072890399999892,
"count": 1,
"is_parallel": true,
"self": 0.00021725099998093356,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005116530000179864,
"count": 2,
"is_parallel": true,
"self": 0.0005116530000179864
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1307.8198951849472,
"count": 233790,
"is_parallel": true,
"self": 41.13634254683029,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.42147281910368,
"count": 233790,
"is_parallel": true,
"self": 84.42147281910368
},
"communicator.exchange": {
"total": 1089.7428057240368,
"count": 233790,
"is_parallel": true,
"self": 1089.7428057240368
},
"steps_from_proto": {
"total": 92.51927409497645,
"count": 233790,
"is_parallel": true,
"self": 32.480423863884596,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.03885023109186,
"count": 467580,
"is_parallel": true,
"self": 60.03885023109186
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 518.4097909139937,
"count": 233791,
"self": 6.837059864088019,
"children": {
"process_trajectory": {
"total": 163.4896441899064,
"count": 233791,
"self": 162.34547690190678,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1441672879996077,
"count": 10,
"self": 1.1441672879996077
}
}
},
"_update_policy": {
"total": 348.08308685999924,
"count": 97,
"self": 284.9059981540052,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.17708870599404,
"count": 2910,
"self": 63.17708870599404
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.299997145717498e-07,
"count": 1,
"self": 9.299997145717498e-07
},
"TrainerController._save_models": {
"total": 0.10043920499992964,
"count": 1,
"self": 0.0019123669999316917,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09852683799999795,
"count": 1,
"self": 0.09852683799999795
}
}
}
}
}
}
}