ppo-Huggy / run_logs /timers.json
Pablinsv's picture
Huggy
7ece95d
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4066016674041748,
"min": 1.4066016674041748,
"max": 1.4275448322296143,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71555.234375,
"min": 68952.546875,
"max": 76865.1953125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 104.4746835443038,
"min": 83.73728813559322,
"max": 417.7916666666667,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49521.0,
"min": 48906.0,
"max": 50135.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999997.0,
"min": 49702.0,
"max": 1999997.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999997.0,
"min": 49702.0,
"max": 1999997.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.379295587539673,
"min": 0.22037339210510254,
"max": 2.474945545196533,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1127.7861328125,
"min": 26.22443389892578,
"max": 1432.5728759765625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6593419022952456,
"min": 1.905386911470349,
"max": 4.04145915779779,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1734.5280616879463,
"min": 226.74104246497154,
"max": 2290.172306716442,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6593419022952456,
"min": 1.905386911470349,
"max": 4.04145915779779,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1734.5280616879463,
"min": 226.74104246497154,
"max": 2290.172306716442,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017778326445517856,
"min": 0.013448700242558214,
"max": 0.02014412343414733,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05333497933655357,
"min": 0.026897400485116428,
"max": 0.05663213079775839,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04833367040587796,
"min": 0.01954394830390811,
"max": 0.06351757686999109,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14500101121763387,
"min": 0.03908789660781622,
"max": 0.19055273060997327,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.54384881875e-06,
"min": 3.54384881875e-06,
"max": 0.00029536822654392496,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.063154645625e-05,
"min": 1.063154645625e-05,
"max": 0.00084425896858035,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10118125000000001,
"min": 0.10118125000000001,
"max": 0.19845607499999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30354375000000006,
"min": 0.20751494999999998,
"max": 0.5814196500000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.894437500000004e-05,
"min": 6.894437500000004e-05,
"max": 0.0049229581424999995,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020683312500000014,
"min": 0.00020683312500000014,
"max": 0.014072840534999997,
"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": "1671797544",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1671799843"
},
"total": 2298.857321211,
"count": 1,
"self": 0.40074230499976693,
"children": {
"run_training.setup": {
"total": 0.20454996300003359,
"count": 1,
"self": 0.20454996300003359
},
"TrainerController.start_learning": {
"total": 2298.2520289430004,
"count": 1,
"self": 3.7873804170271796,
"children": {
"TrainerController._reset_env": {
"total": 8.480384389999983,
"count": 1,
"self": 8.480384389999983
},
"TrainerController.advance": {
"total": 2285.860934687973,
"count": 232369,
"self": 4.0943247238274125,
"children": {
"env_step": {
"total": 1794.9309913080438,
"count": 232369,
"self": 1509.6457070360268,
"children": {
"SubprocessEnvManager._take_step": {
"total": 282.66267043499516,
"count": 232369,
"self": 14.35629995400501,
"children": {
"TorchPolicy.evaluate": {
"total": 268.30637048099015,
"count": 223150,
"self": 67.30529622805807,
"children": {
"TorchPolicy.sample_actions": {
"total": 201.00107425293209,
"count": 223150,
"self": 201.00107425293209
}
}
}
}
},
"workers": {
"total": 2.6226138370217313,
"count": 232369,
"self": 0.0,
"children": {
"worker_root": {
"total": 2290.585266920061,
"count": 232369,
"is_parallel": true,
"self": 1044.7845408709554,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002362026000014339,
"count": 1,
"is_parallel": true,
"self": 0.00027559000005794587,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002086435999956393,
"count": 2,
"is_parallel": true,
"self": 0.002086435999956393
}
}
},
"UnityEnvironment.step": {
"total": 0.02775503300000537,
"count": 1,
"is_parallel": true,
"self": 0.00030594399999017696,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018011999998179817,
"count": 1,
"is_parallel": true,
"self": 0.00018011999998179817
},
"communicator.exchange": {
"total": 0.026561380000032386,
"count": 1,
"is_parallel": true,
"self": 0.026561380000032386
},
"steps_from_proto": {
"total": 0.0007075890000010077,
"count": 1,
"is_parallel": true,
"self": 0.00023978799998758404,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004678010000134236,
"count": 2,
"is_parallel": true,
"self": 0.0004678010000134236
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1245.8007260491054,
"count": 232368,
"is_parallel": true,
"self": 36.151548921074436,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.84138205502575,
"count": 232368,
"is_parallel": true,
"self": 78.84138205502575
},
"communicator.exchange": {
"total": 1034.7219789949477,
"count": 232368,
"is_parallel": true,
"self": 1034.7219789949477
},
"steps_from_proto": {
"total": 96.0858160780574,
"count": 232368,
"is_parallel": true,
"self": 39.583896653015984,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.50191942504142,
"count": 464736,
"is_parallel": true,
"self": 56.50191942504142
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 486.8356186561017,
"count": 232369,
"self": 5.980980857023553,
"children": {
"process_trajectory": {
"total": 150.49696891607812,
"count": 232369,
"self": 149.26503273907838,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2319361769997386,
"count": 10,
"self": 1.2319361769997386
}
}
},
"_update_policy": {
"total": 330.35766888300003,
"count": 97,
"self": 276.15491767200444,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.20275121099559,
"count": 2910,
"self": 54.20275121099559
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0900002962443978e-06,
"count": 1,
"self": 1.0900002962443978e-06
},
"TrainerController._save_models": {
"total": 0.12332835799998065,
"count": 1,
"self": 0.0026183660002061515,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1207099919997745,
"count": 1,
"self": 0.1207099919997745
}
}
}
}
}
}
}