ppo-Huggy / run_logs /timers.json
Stevenson15's picture
Huggy
70de1c1 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4063116312026978,
"min": 1.4063116312026978,
"max": 1.4277739524841309,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69996.3515625,
"min": 68869.7421875,
"max": 77538.921875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 99.51302605210421,
"min": 90.44746376811594,
"max": 382.206106870229,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49657.0,
"min": 48948.0,
"max": 50069.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999944.0,
"min": 49638.0,
"max": 1999944.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999944.0,
"min": 49638.0,
"max": 1999944.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.38437819480896,
"min": 0.031470704823732376,
"max": 2.4103689193725586,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1189.8046875,
"min": 4.09119176864624,
"max": 1317.44873046875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7266051083624006,
"min": 1.77762982914081,
"max": 3.817810852270005,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1859.5759490728378,
"min": 231.09187778830528,
"max": 2004.3762428760529,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7266051083624006,
"min": 1.77762982914081,
"max": 3.817810852270005,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1859.5759490728378,
"min": 231.09187778830528,
"max": 2004.3762428760529,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.0164730279619107,
"min": 0.013567376028125485,
"max": 0.020154842458820592,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0329460559238214,
"min": 0.02713475205625097,
"max": 0.05390969319026529,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05107312245915334,
"min": 0.02294275357077519,
"max": 0.062477280572056766,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.10214624491830668,
"min": 0.04588550714155038,
"max": 0.17881247227390606,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.547198484300009e-06,
"min": 4.547198484300009e-06,
"max": 0.00029532742655752505,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.094396968600018e-06,
"min": 9.094396968600018e-06,
"max": 0.0008441028186323999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1015157,
"min": 0.1015157,
"max": 0.19844247499999995,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.2030314,
"min": 0.2030314,
"max": 0.5813676000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.563343000000015e-05,
"min": 8.563343000000015e-05,
"max": 0.004922279502499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001712668600000003,
"min": 0.0001712668600000003,
"max": 0.01407024324,
"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": "1726411512",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1726414094"
},
"total": 2582.0324727740003,
"count": 1,
"self": 0.7496811470005014,
"children": {
"run_training.setup": {
"total": 0.06576541300000827,
"count": 1,
"self": 0.06576541300000827
},
"TrainerController.start_learning": {
"total": 2581.217026214,
"count": 1,
"self": 4.576559422072478,
"children": {
"TrainerController._reset_env": {
"total": 2.8372124830002576,
"count": 1,
"self": 2.8372124830002576
},
"TrainerController.advance": {
"total": 2573.616839384928,
"count": 231279,
"self": 4.681998912202289,
"children": {
"env_step": {
"total": 2038.8187719210255,
"count": 231279,
"self": 1605.2097866102945,
"children": {
"SubprocessEnvManager._take_step": {
"total": 430.695316444906,
"count": 231279,
"self": 15.690962367950306,
"children": {
"TorchPolicy.evaluate": {
"total": 415.0043540769557,
"count": 222992,
"self": 415.0043540769557
}
}
},
"workers": {
"total": 2.9136688658250023,
"count": 231279,
"self": 0.0,
"children": {
"worker_root": {
"total": 2573.7056238962837,
"count": 231279,
"is_parallel": true,
"self": 1273.7917601012332,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009028780000335246,
"count": 1,
"is_parallel": true,
"self": 0.0002671300003385113,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006357479996950133,
"count": 2,
"is_parallel": true,
"self": 0.0006357479996950133
}
}
},
"UnityEnvironment.step": {
"total": 0.06508503699978974,
"count": 1,
"is_parallel": true,
"self": 0.0003909029992428259,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023244900012286962,
"count": 1,
"is_parallel": true,
"self": 0.00023244900012286962
},
"communicator.exchange": {
"total": 0.06369707100020605,
"count": 1,
"is_parallel": true,
"self": 0.06369707100020605
},
"steps_from_proto": {
"total": 0.0007646140002179891,
"count": 1,
"is_parallel": true,
"self": 0.00022094200085120974,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005436719993667793,
"count": 2,
"is_parallel": true,
"self": 0.0005436719993667793
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1299.9138637950505,
"count": 231278,
"is_parallel": true,
"self": 38.43473962244343,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 87.23516509298042,
"count": 231278,
"is_parallel": true,
"self": 87.23516509298042
},
"communicator.exchange": {
"total": 1080.8050128608638,
"count": 231278,
"is_parallel": true,
"self": 1080.8050128608638
},
"steps_from_proto": {
"total": 93.4389462187628,
"count": 231278,
"is_parallel": true,
"self": 35.46487612298051,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.97407009578228,
"count": 462556,
"is_parallel": true,
"self": 57.97407009578228
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 530.1160685517002,
"count": 231279,
"self": 6.955206326691496,
"children": {
"process_trajectory": {
"total": 156.20504969600415,
"count": 231279,
"self": 154.77244457400366,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4326051220004956,
"count": 10,
"self": 1.4326051220004956
}
}
},
"_update_policy": {
"total": 366.95581252900456,
"count": 96,
"self": 299.3048890790028,
"children": {
"TorchPPOOptimizer.update": {
"total": 67.65092345000176,
"count": 2880,
"self": 67.65092345000176
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3509998098015785e-06,
"count": 1,
"self": 1.3509998098015785e-06
},
"TrainerController._save_models": {
"total": 0.1864135729992995,
"count": 1,
"self": 0.0030569609989470337,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18335661200035247,
"count": 1,
"self": 0.18335661200035247
}
}
}
}
}
}
}