ppo-Huggy / run_logs /timers.json
Haitao Gao
Huggy
eaa81b4
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4050570726394653,
"min": 1.4050570726394653,
"max": 1.426020622253418,
"count": 38
},
"Huggy.Policy.Entropy.sum": {
"value": 72939.3203125,
"min": 66903.8125,
"max": 76439.2734375,
"count": 38
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 115.89461358313817,
"min": 86.32517482517483,
"max": 424.08474576271186,
"count": 38
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49487.0,
"min": 48901.0,
"max": 50188.0,
"count": 38
},
"Huggy.Step.mean": {
"value": 1899980.0,
"min": 49894.0,
"max": 1899980.0,
"count": 38
},
"Huggy.Step.sum": {
"value": 1899980.0,
"min": 49894.0,
"max": 1899980.0,
"count": 38
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.296421766281128,
"min": 0.11437169462442398,
"max": 2.4415011405944824,
"count": 38
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 980.5721435546875,
"min": 13.381487846374512,
"max": 1363.86279296875,
"count": 38
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.4110981755010976,
"min": 1.8727872646771944,
"max": 3.89974290489704,
"count": 38
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1456.5389209389687,
"min": 219.11610996723175,
"max": 2153.6825066804886,
"count": 38
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.4110981755010976,
"min": 1.8727872646771944,
"max": 3.89974290489704,
"count": 38
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1456.5389209389687,
"min": 219.11610996723175,
"max": 2153.6825066804886,
"count": 38
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017477636182350882,
"min": 0.014064774639700772,
"max": 0.01940893497085199,
"count": 38
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05243290854705265,
"min": 0.028129549279401544,
"max": 0.05505332368265954,
"count": 38
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04485268605252107,
"min": 0.02247756922410594,
"max": 0.05978074930608272,
"count": 38
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1345580581575632,
"min": 0.04496274615327517,
"max": 0.1705550586183866,
"count": 38
},
"Huggy.Policy.LearningRate.mean": {
"value": 1.8878993707033333e-05,
"min": 1.8878993707033333e-05,
"max": 0.0002953191765602749,
"count": 38
},
"Huggy.Policy.LearningRate.sum": {
"value": 5.66369811211e-05,
"min": 5.3154032282049985e-05,
"max": 0.0008439048186984,
"count": 38
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10629296666666667,
"min": 0.10629296666666667,
"max": 0.19843972500000004,
"count": 38
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3188789,
"min": 0.21771795,
"max": 0.5813016000000002,
"count": 38
},
"Huggy.Policy.Beta.mean": {
"value": 0.00032401903666666676,
"min": 0.00032401903666666676,
"max": 0.0049221422774999996,
"count": 38
},
"Huggy.Policy.Beta.sum": {
"value": 0.0009720571100000002,
"min": 0.0009041257049999998,
"max": 0.014066949840000002,
"count": 38
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 38
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 38
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1690721330",
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
"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": "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": "1690723645"
},
"total": 2314.609172298,
"count": 1,
"self": 0.24655831900008707,
"children": {
"run_training.setup": {
"total": 0.04625794699995822,
"count": 1,
"self": 0.04625794699995822
},
"TrainerController.start_learning": {
"total": 2314.316356032,
"count": 1,
"self": 4.261116893032067,
"children": {
"TrainerController._reset_env": {
"total": 7.078422620999959,
"count": 1,
"self": 7.078422620999959
},
"TrainerController.advance": {
"total": 2302.789679030968,
"count": 221448,
"self": 4.56653747897235,
"children": {
"env_step": {
"total": 1789.5820417640462,
"count": 221448,
"self": 1510.4548699921827,
"children": {
"SubprocessEnvManager._take_step": {
"total": 276.335693542929,
"count": 221448,
"self": 16.19869004388056,
"children": {
"TorchPolicy.evaluate": {
"total": 260.13700349904843,
"count": 213417,
"self": 260.13700349904843
}
}
},
"workers": {
"total": 2.7914782289344657,
"count": 221447,
"self": 0.0,
"children": {
"worker_root": {
"total": 2306.8512188750633,
"count": 221447,
"is_parallel": true,
"self": 1072.6007975830348,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009767859999101347,
"count": 1,
"is_parallel": true,
"self": 0.00028340499989099044,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006933810000191443,
"count": 2,
"is_parallel": true,
"self": 0.0006933810000191443
}
}
},
"UnityEnvironment.step": {
"total": 0.048977984000089236,
"count": 1,
"is_parallel": true,
"self": 0.00040294700011145324,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00025828399998317764,
"count": 1,
"is_parallel": true,
"self": 0.00025828399998317764
},
"communicator.exchange": {
"total": 0.047516879999989214,
"count": 1,
"is_parallel": true,
"self": 0.047516879999989214
},
"steps_from_proto": {
"total": 0.0007998730000053911,
"count": 1,
"is_parallel": true,
"self": 0.0002626739999413985,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005371990000639926,
"count": 2,
"is_parallel": true,
"self": 0.0005371990000639926
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1234.2504212920285,
"count": 221446,
"is_parallel": true,
"self": 38.89298537719105,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 76.83585470294145,
"count": 221446,
"is_parallel": true,
"self": 76.83585470294145
},
"communicator.exchange": {
"total": 1026.4453620359395,
"count": 221446,
"is_parallel": true,
"self": 1026.4453620359395
},
"steps_from_proto": {
"total": 92.07621917595645,
"count": 221446,
"is_parallel": true,
"self": 33.29596179303428,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.78025738292217,
"count": 442892,
"is_parallel": true,
"self": 58.78025738292217
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 508.6410997879491,
"count": 221447,
"self": 6.275002189987731,
"children": {
"process_trajectory": {
"total": 125.70090597696048,
"count": 221447,
"self": 124.27717311896095,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4237328579995392,
"count": 9,
"self": 1.4237328579995392
}
}
},
"_update_policy": {
"total": 376.6651916210009,
"count": 92,
"self": 320.0965919119981,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.5685997090028,
"count": 2760,
"self": 56.5685997090028
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.913799997055321e-05,
"count": 1,
"self": 1.913799997055321e-05
},
"TrainerController._save_models": {
"total": 0.1871183490002295,
"count": 1,
"self": 0.0026988490003532206,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18441949999987628,
"count": 1,
"self": 0.18441949999987628
}
}
}
}
}
}
}