ppo-Huggy / run_logs /timers.json
InfiniteEcho's picture
Huggy
1e97df5 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4055190086364746,
"min": 1.4055190086364746,
"max": 1.4256566762924194,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70935.140625,
"min": 67923.8046875,
"max": 78849.3125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 68.76011157601116,
"min": 68.76011157601116,
"max": 435.7130434782609,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49301.0,
"min": 49232.0,
"max": 50107.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999983.0,
"min": 49693.0,
"max": 1999983.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999983.0,
"min": 49693.0,
"max": 1999983.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.494084358215332,
"min": 0.07740034908056259,
"max": 2.579319477081299,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1788.258544921875,
"min": 8.823639869689941,
"max": 1788.258544921875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.790824013690736,
"min": 1.8222089605896097,
"max": 4.135892853186124,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2718.0208178162575,
"min": 207.7318215072155,
"max": 2721.417497396469,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.790824013690736,
"min": 1.8222089605896097,
"max": 4.135892853186124,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2718.0208178162575,
"min": 207.7318215072155,
"max": 2721.417497396469,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01594307423155341,
"min": 0.013845784268293452,
"max": 0.020342615506342553,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04782922269466023,
"min": 0.027691568536586903,
"max": 0.05902952877028535,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06380774420168665,
"min": 0.022447335751106343,
"max": 0.06380774420168665,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.19142323260505995,
"min": 0.044894671502212685,
"max": 0.19142323260505995,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.894998701700001e-06,
"min": 3.894998701700001e-06,
"max": 0.00029535825154724995,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1684996105100004e-05,
"min": 1.1684996105100004e-05,
"max": 0.0008439954186681999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10129830000000001,
"min": 0.10129830000000001,
"max": 0.19845275,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3038949,
"min": 0.20773035,
"max": 0.5813318000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.478517000000002e-05,
"min": 7.478517000000002e-05,
"max": 0.004922792225,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022435551000000008,
"min": 0.00022435551000000008,
"max": 0.014068456819999998,
"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": "1719600311",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1719602737"
},
"total": 2426.1112146689998,
"count": 1,
"self": 0.4514452429998528,
"children": {
"run_training.setup": {
"total": 0.05984780500000397,
"count": 1,
"self": 0.05984780500000397
},
"TrainerController.start_learning": {
"total": 2425.599921621,
"count": 1,
"self": 4.484289076908681,
"children": {
"TrainerController._reset_env": {
"total": 3.0341841030000296,
"count": 1,
"self": 3.0341841030000296
},
"TrainerController.advance": {
"total": 2417.971299168091,
"count": 233558,
"self": 4.670437951025178,
"children": {
"env_step": {
"total": 1905.021229785087,
"count": 233558,
"self": 1579.9478626110554,
"children": {
"SubprocessEnvManager._take_step": {
"total": 322.15245894400925,
"count": 233558,
"self": 16.15318891604886,
"children": {
"TorchPolicy.evaluate": {
"total": 305.9992700279604,
"count": 222953,
"self": 305.9992700279604
}
}
},
"workers": {
"total": 2.9209082300224054,
"count": 233558,
"self": 0.0,
"children": {
"worker_root": {
"total": 2418.5293584500173,
"count": 233558,
"is_parallel": true,
"self": 1145.7289108240245,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008594369999173068,
"count": 1,
"is_parallel": true,
"self": 0.00020824699993227114,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006511899999850357,
"count": 2,
"is_parallel": true,
"self": 0.0006511899999850357
}
}
},
"UnityEnvironment.step": {
"total": 0.029039844999942943,
"count": 1,
"is_parallel": true,
"self": 0.00036337299991373584,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019448600005489425,
"count": 1,
"is_parallel": true,
"self": 0.00019448600005489425
},
"communicator.exchange": {
"total": 0.027755272000035802,
"count": 1,
"is_parallel": true,
"self": 0.027755272000035802
},
"steps_from_proto": {
"total": 0.0007267139999385108,
"count": 1,
"is_parallel": true,
"self": 0.00018801700002768484,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000538696999910826,
"count": 2,
"is_parallel": true,
"self": 0.000538696999910826
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1272.8004476259928,
"count": 233557,
"is_parallel": true,
"self": 39.25750000889684,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.33209236492996,
"count": 233557,
"is_parallel": true,
"self": 80.33209236492996
},
"communicator.exchange": {
"total": 1062.4780110220827,
"count": 233557,
"is_parallel": true,
"self": 1062.4780110220827
},
"steps_from_proto": {
"total": 90.7328442300834,
"count": 233557,
"is_parallel": true,
"self": 32.33072466527517,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.40211956480823,
"count": 467114,
"is_parallel": true,
"self": 58.40211956480823
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 508.2796314319788,
"count": 233558,
"self": 6.694564440026966,
"children": {
"process_trajectory": {
"total": 164.20645746695254,
"count": 233558,
"self": 162.91945214695238,
"children": {
"RLTrainer._checkpoint": {
"total": 1.287005320000162,
"count": 10,
"self": 1.287005320000162
}
}
},
"_update_policy": {
"total": 337.3786095249993,
"count": 97,
"self": 272.35223433699207,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.02637518800725,
"count": 2910,
"self": 65.02637518800725
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1150000318593811e-06,
"count": 1,
"self": 1.1150000318593811e-06
},
"TrainerController._save_models": {
"total": 0.11014815800035649,
"count": 1,
"self": 0.0019145340006616607,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10823362399969483,
"count": 1,
"self": 0.10823362399969483
}
}
}
}
}
}
}