ppo-Huggy / run_logs /timers.json
donglinbai's picture
Huggy
b350f6c verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4086365699768066,
"min": 1.4086365699768066,
"max": 1.4298640489578247,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68125.890625,
"min": 67794.1171875,
"max": 77920.328125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 101.39587628865979,
"min": 80.82978723404256,
"max": 375.17910447761193,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49177.0,
"min": 49156.0,
"max": 50274.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999996.0,
"min": 49823.0,
"max": 1999996.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999996.0,
"min": 49823.0,
"max": 1999996.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3205716609954834,
"min": 0.13916486501693726,
"max": 2.491133689880371,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1125.477294921875,
"min": 18.508926391601562,
"max": 1455.525634765625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.4875472114258206,
"min": 1.8158728912808841,
"max": 3.9887163779635317,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1691.460397541523,
"min": 241.5110945403576,
"max": 2275.341480910778,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.4875472114258206,
"min": 1.8158728912808841,
"max": 3.9887163779635317,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1691.460397541523,
"min": 241.5110945403576,
"max": 2275.341480910778,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01677595538413799,
"min": 0.014305480771872681,
"max": 0.02127525955729652,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05032786615241397,
"min": 0.028610961543745362,
"max": 0.05759036088323531,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.046710513118240565,
"min": 0.022234599106013775,
"max": 0.06545011388758819,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1401315393547217,
"min": 0.04446919821202755,
"max": 0.17249447169403234,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.416148861316659e-06,
"min": 3.416148861316659e-06,
"max": 0.00029528775157075,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0248446583949976e-05,
"min": 1.0248446583949976e-05,
"max": 0.0008440873686375498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10113868333333335,
"min": 0.10113868333333335,
"max": 0.19842925000000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30341605000000005,
"min": 0.20747730000000003,
"max": 0.5813624500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.682029833333322e-05,
"min": 6.682029833333322e-05,
"max": 0.004921619574999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020046089499999966,
"min": 0.00020046089499999966,
"max": 0.014069986255,
"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": "1745479103",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1745481528"
},
"total": 2424.3672540490006,
"count": 1,
"self": 0.4482543160006571,
"children": {
"run_training.setup": {
"total": 0.03080252700010533,
"count": 1,
"self": 0.03080252700010533
},
"TrainerController.start_learning": {
"total": 2423.888197206,
"count": 1,
"self": 4.261145400801979,
"children": {
"TrainerController._reset_env": {
"total": 3.3631721239999024,
"count": 1,
"self": 3.3631721239999024
},
"TrainerController.advance": {
"total": 2416.158744781198,
"count": 232153,
"self": 4.562957315356925,
"children": {
"env_step": {
"total": 1925.2415434299342,
"count": 232153,
"self": 1518.6673429812545,
"children": {
"SubprocessEnvManager._take_step": {
"total": 403.9497842829114,
"count": 232153,
"self": 15.559934764877653,
"children": {
"TorchPolicy.evaluate": {
"total": 388.38984951803377,
"count": 222932,
"self": 388.38984951803377
}
}
},
"workers": {
"total": 2.6244161657682525,
"count": 232153,
"self": 0.0,
"children": {
"worker_root": {
"total": 2416.4440420190485,
"count": 232153,
"is_parallel": true,
"self": 1175.9817085679715,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000877076000051602,
"count": 1,
"is_parallel": true,
"self": 0.00023562900059914682,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006414469994524552,
"count": 2,
"is_parallel": true,
"self": 0.0006414469994524552
}
}
},
"UnityEnvironment.step": {
"total": 0.03053319599985116,
"count": 1,
"is_parallel": true,
"self": 0.0003256959998907405,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002046399999926507,
"count": 1,
"is_parallel": true,
"self": 0.0002046399999926507
},
"communicator.exchange": {
"total": 0.029334715999993932,
"count": 1,
"is_parallel": true,
"self": 0.029334715999993932
},
"steps_from_proto": {
"total": 0.0006681439999738359,
"count": 1,
"is_parallel": true,
"self": 0.0001900039997053682,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004781400002684677,
"count": 2,
"is_parallel": true,
"self": 0.0004781400002684677
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1240.462333451077,
"count": 232152,
"is_parallel": true,
"self": 37.06484166373548,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.82962101932162,
"count": 232152,
"is_parallel": true,
"self": 80.82962101932162
},
"communicator.exchange": {
"total": 1035.4930168000978,
"count": 232152,
"is_parallel": true,
"self": 1035.4930168000978
},
"steps_from_proto": {
"total": 87.07485396792208,
"count": 232152,
"is_parallel": true,
"self": 32.2541756985911,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.82067826933098,
"count": 464304,
"is_parallel": true,
"self": 54.82067826933098
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 486.35424403590696,
"count": 232153,
"self": 6.377993278954364,
"children": {
"process_trajectory": {
"total": 158.0508943029572,
"count": 232153,
"self": 156.8331809209567,
"children": {
"RLTrainer._checkpoint": {
"total": 1.217713382000511,
"count": 10,
"self": 1.217713382000511
}
}
},
"_update_policy": {
"total": 321.9253564539954,
"count": 97,
"self": 256.5704251229895,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.3549313310059,
"count": 2910,
"self": 65.3549313310059
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.449995559407398e-07,
"count": 1,
"self": 9.449995559407398e-07
},
"TrainerController._save_models": {
"total": 0.10513395500038314,
"count": 1,
"self": 0.0015648059998056851,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10356914900057745,
"count": 1,
"self": 0.10356914900057745
}
}
}
}
}
}
}