ppo-Huggy / run_logs /timers.json
tstenborg's picture
Huggy
e334c3b verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4074490070343018,
"min": 1.4074490070343018,
"max": 1.428961157798767,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71014.25,
"min": 67487.09375,
"max": 78616.8203125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 78.91800643086816,
"min": 76.23183925811438,
"max": 423.83898305084745,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49087.0,
"min": 48895.0,
"max": 50133.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999914.0,
"min": 49921.0,
"max": 1999914.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999914.0,
"min": 49921.0,
"max": 1999914.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4514341354370117,
"min": 0.11006999760866165,
"max": 2.507070302963257,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1524.7919921875,
"min": 12.878190040588379,
"max": 1593.7734375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.776204021413993,
"min": 1.9265294834079905,
"max": 3.9753669625662362,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2348.798901319504,
"min": 225.4039495587349,
"max": 2496.7874532341957,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.776204021413993,
"min": 1.9265294834079905,
"max": 3.9753669625662362,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2348.798901319504,
"min": 225.4039495587349,
"max": 2496.7874532341957,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014020844470522006,
"min": 0.012976026730514907,
"max": 0.02061840474246613,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04206253341156602,
"min": 0.025952053461029814,
"max": 0.0551855022931098,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06415557981365257,
"min": 0.021179776359349492,
"max": 0.06636601158728203,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.19246673944095768,
"min": 0.042359552718698984,
"max": 0.19522069779535134,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6108487964166735e-06,
"min": 3.6108487964166735e-06,
"max": 0.0002952829515723499,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0832546389250021e-05,
"min": 1.0832546389250021e-05,
"max": 0.0008439391686869501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10120358333333335,
"min": 0.10120358333333335,
"max": 0.19842764999999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30361075000000004,
"min": 0.20753705000000003,
"max": 0.5813130499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.005880833333347e-05,
"min": 7.005880833333347e-05,
"max": 0.004921539734999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002101764250000004,
"min": 0.0002101764250000004,
"max": 0.014067521195000003,
"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": "1758361273",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1758364276"
},
"total": 3002.678861576,
"count": 1,
"self": 0.43815758400023697,
"children": {
"run_training.setup": {
"total": 0.022398499000019,
"count": 1,
"self": 0.022398499000019
},
"TrainerController.start_learning": {
"total": 3002.218305493,
"count": 1,
"self": 6.129023824973046,
"children": {
"TrainerController._reset_env": {
"total": 3.4265281579999964,
"count": 1,
"self": 3.4265281579999964
},
"TrainerController.advance": {
"total": 2992.599799013027,
"count": 232951,
"self": 5.6265513760281465,
"children": {
"env_step": {
"total": 1972.1792050948936,
"count": 232951,
"self": 1644.6606665028073,
"children": {
"SubprocessEnvManager._take_step": {
"total": 323.63180260910326,
"count": 232951,
"self": 17.766930781103042,
"children": {
"TorchPolicy.evaluate": {
"total": 305.8648718280002,
"count": 222965,
"self": 305.8648718280002
}
}
},
"workers": {
"total": 3.886735982983055,
"count": 232951,
"self": 0.0,
"children": {
"worker_root": {
"total": 2993.2458863399943,
"count": 232951,
"is_parallel": true,
"self": 1681.3491077289639,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0006305800000063755,
"count": 1,
"is_parallel": true,
"self": 0.00016246199993474875,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00046811800007162674,
"count": 2,
"is_parallel": true,
"self": 0.00046811800007162674
}
}
},
"UnityEnvironment.step": {
"total": 0.02802406799992241,
"count": 1,
"is_parallel": true,
"self": 0.0003326010000819224,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019998899995243846,
"count": 1,
"is_parallel": true,
"self": 0.00019998899995243846
},
"communicator.exchange": {
"total": 0.02679595799997969,
"count": 1,
"is_parallel": true,
"self": 0.02679595799997969
},
"steps_from_proto": {
"total": 0.0006955199999083561,
"count": 1,
"is_parallel": true,
"self": 0.0002135499998985324,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004819700000098237,
"count": 2,
"is_parallel": true,
"self": 0.0004819700000098237
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1311.8967786110304,
"count": 232950,
"is_parallel": true,
"self": 41.6014162951094,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 77.2105750779674,
"count": 232950,
"is_parallel": true,
"self": 77.2105750779674
},
"communicator.exchange": {
"total": 1098.1052468439739,
"count": 232950,
"is_parallel": true,
"self": 1098.1052468439739
},
"steps_from_proto": {
"total": 94.97954039397973,
"count": 232950,
"is_parallel": true,
"self": 30.912052128099845,
"children": {
"_process_rank_one_or_two_observation": {
"total": 64.06748826587989,
"count": 465900,
"is_parallel": true,
"self": 64.06748826587989
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1014.7940425421057,
"count": 232951,
"self": 9.048910185181626,
"children": {
"process_trajectory": {
"total": 173.881833275923,
"count": 232951,
"self": 173.14690814292328,
"children": {
"RLTrainer._checkpoint": {
"total": 0.734925132999706,
"count": 10,
"self": 0.734925132999706
}
}
},
"_update_policy": {
"total": 831.8632990810011,
"count": 97,
"self": 214.89696300999492,
"children": {
"TorchPPOOptimizer.update": {
"total": 616.9663360710061,
"count": 2910,
"self": 616.9663360710061
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.500001058564521e-07,
"count": 1,
"self": 8.500001058564521e-07
},
"TrainerController._save_models": {
"total": 0.06295364699963102,
"count": 1,
"self": 0.0017211499998666113,
"children": {
"RLTrainer._checkpoint": {
"total": 0.06123249699976441,
"count": 1,
"self": 0.06123249699976441
}
}
}
}
}
}
}