ppo-Huggy / run_logs /timers.json
Osborn-bh's picture
Huggy
452e6af
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4053850173950195,
"min": 1.4053850173950195,
"max": 1.429818034172058,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71937.4453125,
"min": 68741.390625,
"max": 77806.0,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 102.40286298568508,
"min": 91.01657458563535,
"max": 390.8139534883721,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 50075.0,
"min": 49173.0,
"max": 50415.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999853.0,
"min": 49838.0,
"max": 1999853.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999853.0,
"min": 49838.0,
"max": 1999853.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.416335105895996,
"min": 0.1704907864332199,
"max": 2.4372103214263916,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1181.587890625,
"min": 21.82282066345215,
"max": 1303.907470703125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6342934443175428,
"min": 1.7723646587692201,
"max": 3.846730364875479,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1777.1694942712784,
"min": 226.86267632246017,
"max": 2050.60491669178,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6342934443175428,
"min": 1.7723646587692201,
"max": 3.846730364875479,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1777.1694942712784,
"min": 226.86267632246017,
"max": 2050.60491669178,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015458111168118195,
"min": 0.012934849816762531,
"max": 0.019495508225509182,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03091622233623639,
"min": 0.025951541691999105,
"max": 0.05508601671293339,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0465976666038235,
"min": 0.021011566960563263,
"max": 0.06315291143125958,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.093195333207647,
"min": 0.042023133921126526,
"max": 0.1894587342937787,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.445723518124996e-06,
"min": 4.445723518124996e-06,
"max": 0.0002953396515534499,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.891447036249993e-06,
"min": 8.891447036249993e-06,
"max": 0.0008439427686857499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.101481875,
"min": 0.101481875,
"max": 0.19844655000000008,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20296375,
"min": 0.20296375,
"max": 0.5813142500000003,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.394556249999996e-05,
"min": 8.394556249999996e-05,
"max": 0.004922482845000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00016789112499999992,
"min": 0.00016789112499999992,
"max": 0.014067581075000002,
"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": "1700833834",
"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": "1700836452"
},
"total": 2617.9143059059998,
"count": 1,
"self": 0.7706469909999214,
"children": {
"run_training.setup": {
"total": 0.07480577000001176,
"count": 1,
"self": 0.07480577000001176
},
"TrainerController.start_learning": {
"total": 2617.0688531449996,
"count": 1,
"self": 4.716943814950355,
"children": {
"TrainerController._reset_env": {
"total": 10.623718709000059,
"count": 1,
"self": 10.623718709000059
},
"TrainerController.advance": {
"total": 2601.570303363049,
"count": 231283,
"self": 5.224639946151001,
"children": {
"env_step": {
"total": 2078.9355976319257,
"count": 231283,
"self": 1709.1564011778985,
"children": {
"SubprocessEnvManager._take_step": {
"total": 366.6270963329762,
"count": 231283,
"self": 18.640435380955523,
"children": {
"TorchPolicy.evaluate": {
"total": 347.98666095202066,
"count": 222998,
"self": 347.98666095202066
}
}
},
"workers": {
"total": 3.152100121051035,
"count": 231283,
"self": 0.0,
"children": {
"worker_root": {
"total": 2609.1999433419996,
"count": 231283,
"is_parallel": true,
"self": 1226.7305199940245,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001082932000144865,
"count": 1,
"is_parallel": true,
"self": 0.0003245650000280875,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007583670001167775,
"count": 2,
"is_parallel": true,
"self": 0.0007583670001167775
}
}
},
"UnityEnvironment.step": {
"total": 0.05100218400002632,
"count": 1,
"is_parallel": true,
"self": 0.0003481309995549964,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002623760001370101,
"count": 1,
"is_parallel": true,
"self": 0.0002623760001370101
},
"communicator.exchange": {
"total": 0.04955282000014449,
"count": 1,
"is_parallel": true,
"self": 0.04955282000014449
},
"steps_from_proto": {
"total": 0.0008388570001898188,
"count": 1,
"is_parallel": true,
"self": 0.00025091700013035734,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005879400000594615,
"count": 2,
"is_parallel": true,
"self": 0.0005879400000594615
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1382.4694233479752,
"count": 231282,
"is_parallel": true,
"self": 42.391993686745536,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 92.46829759316051,
"count": 231282,
"is_parallel": true,
"self": 92.46829759316051
},
"communicator.exchange": {
"total": 1151.6262645970255,
"count": 231282,
"is_parallel": true,
"self": 1151.6262645970255
},
"steps_from_proto": {
"total": 95.98286747104362,
"count": 231282,
"is_parallel": true,
"self": 35.8652479247678,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.11761954627582,
"count": 462564,
"is_parallel": true,
"self": 60.11761954627582
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 517.410065784972,
"count": 231283,
"self": 7.1272133978291095,
"children": {
"process_trajectory": {
"total": 165.84951518814364,
"count": 231283,
"self": 164.56870935814368,
"children": {
"RLTrainer._checkpoint": {
"total": 1.280805829999963,
"count": 10,
"self": 1.280805829999963
}
}
},
"_update_policy": {
"total": 344.4333371989992,
"count": 96,
"self": 281.2086173160096,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.224719882989575,
"count": 2880,
"self": 63.224719882989575
}
}
}
}
}
}
},
"trainer_threads": {
"total": 2.240999947389355e-06,
"count": 1,
"self": 2.240999947389355e-06
},
"TrainerController._save_models": {
"total": 0.1578850170003534,
"count": 1,
"self": 0.0028215990005264757,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15506341799982692,
"count": 1,
"self": 0.15506341799982692
}
}
}
}
}
}
}