ppo-Huggy / run_logs /timers.json
mabrouk's picture
Huggy
f4f4e13
raw
history blame
17.4 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4015578031539917,
"min": 1.4015578031539917,
"max": 1.4274113178253174,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70679.15625,
"min": 68680.09375,
"max": 76796.90625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 85.91943957968476,
"min": 79.07211538461539,
"max": 430.3103448275862,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49060.0,
"min": 48731.0,
"max": 50090.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999932.0,
"min": 49816.0,
"max": 1999932.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999932.0,
"min": 49816.0,
"max": 1999932.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.5079665184020996,
"min": 0.009791751392185688,
"max": 2.5329530239105225,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1432.048828125,
"min": 1.126051425933838,
"max": 1527.426025390625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.810363988220796,
"min": 1.7978076914082404,
"max": 4.081183781034203,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2175.7178372740746,
"min": 206.74788451194763,
"max": 2463.7591849565506,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.810363988220796,
"min": 1.7978076914082404,
"max": 4.081183781034203,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2175.7178372740746,
"min": 206.74788451194763,
"max": 2463.7591849565506,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017369228626840694,
"min": 0.01421327985735843,
"max": 0.021899123128666056,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05210768588052209,
"min": 0.02842655971471686,
"max": 0.05807128460728563,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.057304246889220346,
"min": 0.02400232611431016,
"max": 0.0636141315723459,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17191274066766105,
"min": 0.0482170586163799,
"max": 0.17540852365394433,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4757488414499978e-06,
"min": 3.4757488414499978e-06,
"max": 0.00029528647657117507,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0427246524349993e-05,
"min": 1.0427246524349993e-05,
"max": 0.0008439184686938499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10115855,
"min": 0.10115855,
"max": 0.19842882499999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30347565,
"min": 0.2075133,
"max": 0.58130615,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.781164499999996e-05,
"min": 6.781164499999996e-05,
"max": 0.004921598367500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020343493499999987,
"min": 0.00020343493499999987,
"max": 0.014067176885,
"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": "1696458798",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=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": "1696461450"
},
"total": 2651.377533401,
"count": 1,
"self": 0.44152527300002475,
"children": {
"run_training.setup": {
"total": 0.047971798999981274,
"count": 1,
"self": 0.047971798999981274
},
"TrainerController.start_learning": {
"total": 2650.888036329,
"count": 1,
"self": 5.140646500004095,
"children": {
"TrainerController._reset_env": {
"total": 4.108962177999956,
"count": 1,
"self": 4.108962177999956
},
"TrainerController.advance": {
"total": 2641.5246119919957,
"count": 232881,
"self": 5.061602033919826,
"children": {
"env_step": {
"total": 2061.807191765014,
"count": 232881,
"self": 1737.8189928359827,
"children": {
"SubprocessEnvManager._take_step": {
"total": 320.6501382261174,
"count": 232881,
"self": 18.69911058419183,
"children": {
"TorchPolicy.evaluate": {
"total": 301.9510276419256,
"count": 222953,
"self": 301.9510276419256
}
}
},
"workers": {
"total": 3.3380607029138787,
"count": 232881,
"self": 0.0,
"children": {
"worker_root": {
"total": 2642.308537778945,
"count": 232881,
"is_parallel": true,
"self": 1226.6431088169118,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009910539999964385,
"count": 1,
"is_parallel": true,
"self": 0.00026232600004050255,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000728727999955936,
"count": 2,
"is_parallel": true,
"self": 0.000728727999955936
}
}
},
"UnityEnvironment.step": {
"total": 0.03190778399999772,
"count": 1,
"is_parallel": true,
"self": 0.00031945099999575177,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023480200002268248,
"count": 1,
"is_parallel": true,
"self": 0.00023480200002268248
},
"communicator.exchange": {
"total": 0.030594753999992008,
"count": 1,
"is_parallel": true,
"self": 0.030594753999992008
},
"steps_from_proto": {
"total": 0.0007587769999872762,
"count": 1,
"is_parallel": true,
"self": 0.00021545699996750045,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005433200000197758,
"count": 2,
"is_parallel": true,
"self": 0.0005433200000197758
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1415.665428962033,
"count": 232880,
"is_parallel": true,
"self": 41.59336242808013,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 89.6379278629384,
"count": 232880,
"is_parallel": true,
"self": 89.6379278629384
},
"communicator.exchange": {
"total": 1177.3631176090212,
"count": 232880,
"is_parallel": true,
"self": 1177.3631176090212
},
"steps_from_proto": {
"total": 107.0710210619934,
"count": 232880,
"is_parallel": true,
"self": 40.85556680003481,
"children": {
"_process_rank_one_or_two_observation": {
"total": 66.2154542619586,
"count": 465760,
"is_parallel": true,
"self": 66.2154542619586
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 574.6558181930617,
"count": 232881,
"self": 7.5855103352720334,
"children": {
"process_trajectory": {
"total": 153.6447479317871,
"count": 232881,
"self": 152.10137274078664,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5433751910004503,
"count": 10,
"self": 1.5433751910004503
}
}
},
"_update_policy": {
"total": 413.4255599260026,
"count": 97,
"self": 351.9685838660091,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.45697605999351,
"count": 2910,
"self": 61.45697605999351
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1399997674743645e-06,
"count": 1,
"self": 1.1399997674743645e-06
},
"TrainerController._save_models": {
"total": 0.11381451900024331,
"count": 1,
"self": 0.0019055450002269936,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11190897400001631,
"count": 1,
"self": 0.11190897400001631
}
}
}
}
}
}
}