ppo-Huggy / run_logs /timers.json
tux's picture
Huggy
a795ecc
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.403659701347351,
"min": 1.403659701347351,
"max": 1.4262497425079346,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70957.8046875,
"min": 68776.1953125,
"max": 75915.640625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 89.13200723327306,
"min": 78.0886075949367,
"max": 398.46031746031747,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49290.0,
"min": 48892.0,
"max": 50206.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999953.0,
"min": 49877.0,
"max": 1999953.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999953.0,
"min": 49877.0,
"max": 1999953.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.452713966369629,
"min": 0.016194358468055725,
"max": 2.512305974960327,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1356.350830078125,
"min": 2.024294853210449,
"max": 1532.98974609375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7027116423274036,
"min": 1.7847367353439332,
"max": 4.03184910606001,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2047.5995382070541,
"min": 223.09209191799164,
"max": 2471.3641137480736,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7027116423274036,
"min": 1.7847367353439332,
"max": 4.03184910606001,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2047.5995382070541,
"min": 223.09209191799164,
"max": 2471.3641137480736,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01677429958104363,
"min": 0.014637135539750388,
"max": 0.02110412271770959,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05032289874313089,
"min": 0.029412936157314107,
"max": 0.0561394096982743,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05634964928030967,
"min": 0.023154096522678934,
"max": 0.060514521102110544,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16904894784092903,
"min": 0.04630819304535787,
"max": 0.1797528088092804,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.1400489533499915e-06,
"min": 3.1400489533499915e-06,
"max": 0.00029531572656142494,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.420146860049974e-06,
"min": 9.420146860049974e-06,
"max": 0.0008440497186500998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10104665,
"min": 0.10104665,
"max": 0.1984385750000001,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30313995,
"min": 0.20728260000000004,
"max": 0.5813499,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.222783499999986e-05,
"min": 6.222783499999986e-05,
"max": 0.0049220848925,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00018668350499999957,
"min": 0.00018668350499999957,
"max": 0.014069360009999999,
"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": "1686808914",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"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": "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": "1686811492"
},
"total": 2577.876827557,
"count": 1,
"self": 0.440717912999844,
"children": {
"run_training.setup": {
"total": 0.04608512000004339,
"count": 1,
"self": 0.04608512000004339
},
"TrainerController.start_learning": {
"total": 2577.390024524,
"count": 1,
"self": 5.113588378965687,
"children": {
"TrainerController._reset_env": {
"total": 4.322424952000006,
"count": 1,
"self": 4.322424952000006
},
"TrainerController.advance": {
"total": 2567.8225963860345,
"count": 233093,
"self": 5.073269320120744,
"children": {
"env_step": {
"total": 2022.6330683729923,
"count": 233093,
"self": 1706.9627086109467,
"children": {
"SubprocessEnvManager._take_step": {
"total": 312.5616018759699,
"count": 233093,
"self": 18.374559514935072,
"children": {
"TorchPolicy.evaluate": {
"total": 294.18704236103486,
"count": 223019,
"self": 294.18704236103486
}
}
},
"workers": {
"total": 3.1087578860757503,
"count": 233093,
"self": 0.0,
"children": {
"worker_root": {
"total": 2569.188454883057,
"count": 233093,
"is_parallel": true,
"self": 1176.1021135640763,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0013283989999877122,
"count": 1,
"is_parallel": true,
"self": 0.00034610199992357593,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009822970000641362,
"count": 2,
"is_parallel": true,
"self": 0.0009822970000641362
}
}
},
"UnityEnvironment.step": {
"total": 0.0849255279999852,
"count": 1,
"is_parallel": true,
"self": 0.00033748100003094805,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021169500001860797,
"count": 1,
"is_parallel": true,
"self": 0.00021169500001860797
},
"communicator.exchange": {
"total": 0.08356624699996473,
"count": 1,
"is_parallel": true,
"self": 0.08356624699996473
},
"steps_from_proto": {
"total": 0.0008101049999709176,
"count": 1,
"is_parallel": true,
"self": 0.00025434299999460563,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005557619999763119,
"count": 2,
"is_parallel": true,
"self": 0.0005557619999763119
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1393.0863413189809,
"count": 233092,
"is_parallel": true,
"self": 41.137700740020364,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 86.56953160097686,
"count": 233092,
"is_parallel": true,
"self": 86.56953160097686
},
"communicator.exchange": {
"total": 1164.9368022080164,
"count": 233092,
"is_parallel": true,
"self": 1164.9368022080164
},
"steps_from_proto": {
"total": 100.44230676996716,
"count": 233092,
"is_parallel": true,
"self": 38.01043014580563,
"children": {
"_process_rank_one_or_two_observation": {
"total": 62.43187662416153,
"count": 466184,
"is_parallel": true,
"self": 62.43187662416153
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 540.1162586929215,
"count": 233093,
"self": 7.132454711857463,
"children": {
"process_trajectory": {
"total": 149.30005314706455,
"count": 233093,
"self": 147.88333734506443,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4167158020001125,
"count": 10,
"self": 1.4167158020001125
}
}
},
"_update_policy": {
"total": 383.68375083399945,
"count": 97,
"self": 323.2629067170115,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.42084411698795,
"count": 2910,
"self": 60.42084411698795
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1199999789823778e-06,
"count": 1,
"self": 1.1199999789823778e-06
},
"TrainerController._save_models": {
"total": 0.1314136870000766,
"count": 1,
"self": 0.001970185000118363,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12944350199995824,
"count": 1,
"self": 0.12944350199995824
}
}
}
}
}
}
}