ppo-Huggy / run_logs /timers.json
jiudth's picture
Huggy
58a5017 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4055863618850708,
"min": 1.4055863618850708,
"max": 1.4275671243667603,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71381.296875,
"min": 68835.3828125,
"max": 75407.953125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 92.8311444652908,
"min": 81.43564356435644,
"max": 388.1937984496124,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49479.0,
"min": 48837.0,
"max": 50143.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999937.0,
"min": 49821.0,
"max": 1999937.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999937.0,
"min": 49821.0,
"max": 1999937.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4216690063476562,
"min": 0.24439996480941772,
"max": 2.4863739013671875,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1290.7496337890625,
"min": 31.28319549560547,
"max": 1495.085205078125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.728600011086598,
"min": 1.9741729232482612,
"max": 3.9429506208566245,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1987.3438059091568,
"min": 252.69413417577744,
"max": 2364.9005255699158,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.728600011086598,
"min": 1.9741729232482612,
"max": 3.9429506208566245,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1987.3438059091568,
"min": 252.69413417577744,
"max": 2364.9005255699158,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01564856904321156,
"min": 0.013602018212744345,
"max": 0.020778785551374312,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04694570712963468,
"min": 0.02720403642548869,
"max": 0.06233635665412293,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.054975601037343336,
"min": 0.021453339327126744,
"max": 0.06414494663476944,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16492680311203,
"min": 0.04290667865425349,
"max": 0.17435845757524174,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.598148800649997e-06,
"min": 3.598148800649997e-06,
"max": 0.000295275826574725,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.079444640194999e-05,
"min": 1.079444640194999e-05,
"max": 0.0008437771687409499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10119935000000002,
"min": 0.10119935000000002,
"max": 0.198425275,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30359805000000006,
"min": 0.20753504999999994,
"max": 0.58125905,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.984756499999998e-05,
"min": 6.984756499999998e-05,
"max": 0.0049214212225,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020954269499999991,
"min": 0.00020954269499999991,
"max": 0.014064826595,
"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": "1706082761",
"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=Huggy --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1706085105"
},
"total": 2343.6877299750004,
"count": 1,
"self": 0.4486809160002849,
"children": {
"run_training.setup": {
"total": 0.06096505599998636,
"count": 1,
"self": 0.06096505599998636
},
"TrainerController.start_learning": {
"total": 2343.178084003,
"count": 1,
"self": 4.419130868960565,
"children": {
"TrainerController._reset_env": {
"total": 3.5933993080000164,
"count": 1,
"self": 3.5933993080000164
},
"TrainerController.advance": {
"total": 2335.0569868110397,
"count": 232574,
"self": 4.648380385041946,
"children": {
"env_step": {
"total": 1860.1175786630229,
"count": 232574,
"self": 1545.0649847888367,
"children": {
"SubprocessEnvManager._take_step": {
"total": 312.25354847909387,
"count": 232574,
"self": 16.738942289118313,
"children": {
"TorchPolicy.evaluate": {
"total": 295.51460618997555,
"count": 223074,
"self": 295.51460618997555
}
}
},
"workers": {
"total": 2.7990453950922074,
"count": 232574,
"self": 0.0,
"children": {
"worker_root": {
"total": 2336.013414069033,
"count": 232574,
"is_parallel": true,
"self": 1074.5884156069833,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0007300989999521335,
"count": 1,
"is_parallel": true,
"self": 0.00021257199989577202,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005175270000563614,
"count": 2,
"is_parallel": true,
"self": 0.0005175270000563614
}
}
},
"UnityEnvironment.step": {
"total": 0.030143758000008347,
"count": 1,
"is_parallel": true,
"self": 0.0003561759999684,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001984479999919131,
"count": 1,
"is_parallel": true,
"self": 0.0001984479999919131
},
"communicator.exchange": {
"total": 0.02885531100002936,
"count": 1,
"is_parallel": true,
"self": 0.02885531100002936
},
"steps_from_proto": {
"total": 0.0007338230000186741,
"count": 1,
"is_parallel": true,
"self": 0.0001939780000839164,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005398449999347577,
"count": 2,
"is_parallel": true,
"self": 0.0005398449999347577
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1261.4249984620496,
"count": 232573,
"is_parallel": true,
"self": 41.055677045926586,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.63086746209615,
"count": 232573,
"is_parallel": true,
"self": 81.63086746209615
},
"communicator.exchange": {
"total": 1049.3430021510205,
"count": 232573,
"is_parallel": true,
"self": 1049.3430021510205
},
"steps_from_proto": {
"total": 89.39545180300627,
"count": 232573,
"is_parallel": true,
"self": 30.97073011304633,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.42472168995994,
"count": 465146,
"is_parallel": true,
"self": 58.42472168995994
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 470.29102776297475,
"count": 232574,
"self": 6.858439720976435,
"children": {
"process_trajectory": {
"total": 150.88913287400044,
"count": 232574,
"self": 149.76033839700085,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1287944769995875,
"count": 10,
"self": 1.1287944769995875
}
}
},
"_update_policy": {
"total": 312.5434551679979,
"count": 97,
"self": 250.36260325201272,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.18085191598516,
"count": 2910,
"self": 62.18085191598516
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.920002644823398e-07,
"count": 1,
"self": 7.920002644823398e-07
},
"TrainerController._save_models": {
"total": 0.1085662229997979,
"count": 1,
"self": 0.00201965599990217,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10654656699989573,
"count": 1,
"self": 0.10654656699989573
}
}
}
}
}
}
}