ppo-Huggy / run_logs /timers.json
ZeroEW's picture
Huggy
656040c verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.405471682548523,
"min": 1.405471682548523,
"max": 1.4262713193893433,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71244.765625,
"min": 68619.5234375,
"max": 76544.859375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 92.82674199623352,
"min": 82.12479201331115,
"max": 398.22222222222223,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49291.0,
"min": 48968.0,
"max": 50176.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999365.0,
"min": 49723.0,
"max": 1999365.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999365.0,
"min": 49723.0,
"max": 1999365.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.409261465072632,
"min": -0.007317391224205494,
"max": 2.4905102252960205,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1279.31787109375,
"min": -0.914673924446106,
"max": 1477.40380859375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7781426145532038,
"min": 1.7898653635978699,
"max": 3.9725857760438967,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2006.1937283277512,
"min": 223.73317044973373,
"max": 2371.6337082982063,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7781426145532038,
"min": 1.7898653635978699,
"max": 3.9725857760438967,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2006.1937283277512,
"min": 223.73317044973373,
"max": 2371.6337082982063,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.019798864912849646,
"min": 0.011739585729083046,
"max": 0.020173951017689734,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.059396594738548934,
"min": 0.023479171458166092,
"max": 0.059396594738548934,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05675919676820437,
"min": 0.023775832758595544,
"max": 0.06632753531965944,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17027759030461312,
"min": 0.04755166551719109,
"max": 0.19898260595897835,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5272988242666634e-06,
"min": 3.5272988242666634e-06,
"max": 0.00029537617654127495,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.058189647279999e-05,
"min": 1.058189647279999e-05,
"max": 0.0008441062686312498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1011757333333333,
"min": 0.1011757333333333,
"max": 0.198458725,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3035271999999999,
"min": 0.20752645000000003,
"max": 0.5813687499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.866909333333328e-05,
"min": 6.866909333333328e-05,
"max": 0.004923090377499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020600727999999985,
"min": 0.00020600727999999985,
"max": 0.014070300625,
"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": "1743178410",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1743180907"
},
"total": 2497.168788346,
"count": 1,
"self": 0.4385042760000033,
"children": {
"run_training.setup": {
"total": 0.02291913300007309,
"count": 1,
"self": 0.02291913300007309
},
"TrainerController.start_learning": {
"total": 2496.707364937,
"count": 1,
"self": 4.605586955902709,
"children": {
"TrainerController._reset_env": {
"total": 3.3969141039999613,
"count": 1,
"self": 3.3969141039999613
},
"TrainerController.advance": {
"total": 2488.558386843097,
"count": 232368,
"self": 4.559597815240977,
"children": {
"env_step": {
"total": 1990.1757033589352,
"count": 232368,
"self": 1561.2938486217422,
"children": {
"SubprocessEnvManager._take_step": {
"total": 426.0733251211717,
"count": 232368,
"self": 15.919769329163614,
"children": {
"TorchPolicy.evaluate": {
"total": 410.1535557920081,
"count": 222950,
"self": 410.1535557920081
}
}
},
"workers": {
"total": 2.80852961602136,
"count": 232368,
"self": 0.0,
"children": {
"worker_root": {
"total": 2488.8359739538646,
"count": 232368,
"is_parallel": true,
"self": 1216.5058662888136,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010910799999237497,
"count": 1,
"is_parallel": true,
"self": 0.00039606300003924844,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006950169998845013,
"count": 2,
"is_parallel": true,
"self": 0.0006950169998845013
}
}
},
"UnityEnvironment.step": {
"total": 0.04753782200009482,
"count": 1,
"is_parallel": true,
"self": 0.0003338240001085069,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001962300000286632,
"count": 1,
"is_parallel": true,
"self": 0.0001962300000286632
},
"communicator.exchange": {
"total": 0.04628187100001924,
"count": 1,
"is_parallel": true,
"self": 0.04628187100001924
},
"steps_from_proto": {
"total": 0.0007258969999384135,
"count": 1,
"is_parallel": true,
"self": 0.00020908899989535712,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005168080000430564,
"count": 2,
"is_parallel": true,
"self": 0.0005168080000430564
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1272.330107665051,
"count": 232367,
"is_parallel": true,
"self": 37.68557972531471,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.48407243280076,
"count": 232367,
"is_parallel": true,
"self": 80.48407243280076
},
"communicator.exchange": {
"total": 1065.6480575389905,
"count": 232367,
"is_parallel": true,
"self": 1065.6480575389905
},
"steps_from_proto": {
"total": 88.51239796794493,
"count": 232367,
"is_parallel": true,
"self": 30.877334787896757,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.63506318004818,
"count": 464734,
"is_parallel": true,
"self": 57.63506318004818
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 493.82308566892084,
"count": 232368,
"self": 7.096481596806257,
"children": {
"process_trajectory": {
"total": 167.25025172711594,
"count": 232368,
"self": 165.95396079111674,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2962909359991954,
"count": 10,
"self": 1.2962909359991954
}
}
},
"_update_policy": {
"total": 319.47635234499865,
"count": 97,
"self": 252.5776574280028,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.89869491699585,
"count": 2910,
"self": 66.89869491699585
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.010000212583691e-07,
"count": 1,
"self": 9.010000212583691e-07
},
"TrainerController._save_models": {
"total": 0.14647613299985096,
"count": 1,
"self": 0.0020937829995091306,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14438235000034183,
"count": 1,
"self": 0.14438235000034183
}
}
}
}
}
}
}