ppo-Huggy / run_logs /timers.json
francisco-perez-sorrosal's picture
First commit
04a375a verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.415183663368225,
"min": 1.415183663368225,
"max": 1.424683928489685,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71149.7734375,
"min": 68930.96875,
"max": 78176.71875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 90.06375227686704,
"min": 80.33224755700326,
"max": 407.0243902439024,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49445.0,
"min": 48936.0,
"max": 50064.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999915.0,
"min": 49438.0,
"max": 1999915.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999915.0,
"min": 49438.0,
"max": 1999915.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3912031650543213,
"min": -0.05532871559262276,
"max": 2.491377592086792,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1312.7705078125,
"min": -6.75010347366333,
"max": 1472.070556640625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.5944298952003644,
"min": 1.8533180331597563,
"max": 3.9741224895786327,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1973.3420124650002,
"min": 226.10480004549026,
"max": 2300.250617682934,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.5944298952003644,
"min": 1.8533180331597563,
"max": 3.9741224895786327,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1973.3420124650002,
"min": 226.10480004549026,
"max": 2300.250617682934,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.023820463898462346,
"min": 0.02127804233621444,
"max": 0.027244250442890916,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.07146139169538704,
"min": 0.04264774331046889,
"max": 0.07765272695784613,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0569601627273692,
"min": 0.021283635109042128,
"max": 0.06663494314998389,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1708804881821076,
"min": 0.042567270218084256,
"max": 0.19990482944995167,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 1.2139987861000013e-06,
"min": 1.2139987861000013e-06,
"max": 9.844625155375e-05,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 3.641996358300004e-06,
"min": 3.641996358300004e-06,
"max": 0.00028133746866255006,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10121390000000001,
"min": 0.10121390000000001,
"max": 0.19844625000000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3036417,
"min": 0.20757635000000002,
"max": 0.5813374499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.057361000000006e-05,
"min": 7.057361000000006e-05,
"max": 0.004922467875000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002117208300000002,
"min": 0.0002117208300000002,
"max": 0.014068738754999997,
"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": "1711053405",
"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=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1711055884"
},
"total": 2478.7643959290003,
"count": 1,
"self": 0.44245176100002936,
"children": {
"run_training.setup": {
"total": 0.06030739199991331,
"count": 1,
"self": 0.06030739199991331
},
"TrainerController.start_learning": {
"total": 2478.261636776,
"count": 1,
"self": 4.675929665975673,
"children": {
"TrainerController._reset_env": {
"total": 3.0873448109998662,
"count": 1,
"self": 3.0873448109998662
},
"TrainerController.advance": {
"total": 2470.364623831025,
"count": 232760,
"self": 4.714722488834468,
"children": {
"env_step": {
"total": 1972.430806433039,
"count": 232760,
"self": 1627.9980100029295,
"children": {
"SubprocessEnvManager._take_step": {
"total": 341.415922308129,
"count": 232760,
"self": 17.85505601812588,
"children": {
"TorchPolicy.evaluate": {
"total": 323.5608662900031,
"count": 223086,
"self": 323.5608662900031
}
}
},
"workers": {
"total": 3.016874121980436,
"count": 232760,
"self": 0.0,
"children": {
"worker_root": {
"total": 2470.703075888042,
"count": 232760,
"is_parallel": true,
"self": 1162.057012296974,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009500500000285683,
"count": 1,
"is_parallel": true,
"self": 0.0002473570000347536,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007026929999938147,
"count": 2,
"is_parallel": true,
"self": 0.0007026929999938147
}
}
},
"UnityEnvironment.step": {
"total": 0.03313475799996013,
"count": 1,
"is_parallel": true,
"self": 0.00042048199998134805,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023514800000157265,
"count": 1,
"is_parallel": true,
"self": 0.00023514800000157265
},
"communicator.exchange": {
"total": 0.031665753999959634,
"count": 1,
"is_parallel": true,
"self": 0.031665753999959634
},
"steps_from_proto": {
"total": 0.0008133740000175749,
"count": 1,
"is_parallel": true,
"self": 0.00020977200006200292,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000603601999955572,
"count": 2,
"is_parallel": true,
"self": 0.000603601999955572
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1308.6460635910678,
"count": 232759,
"is_parallel": true,
"self": 40.54503151589074,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.99683654913952,
"count": 232759,
"is_parallel": true,
"self": 82.99683654913952
},
"communicator.exchange": {
"total": 1090.8104082539885,
"count": 232759,
"is_parallel": true,
"self": 1090.8104082539885
},
"steps_from_proto": {
"total": 94.29378727204903,
"count": 232759,
"is_parallel": true,
"self": 33.37042866211277,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.92335860993626,
"count": 465518,
"is_parallel": true,
"self": 60.92335860993626
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 493.2190949091514,
"count": 232760,
"self": 7.172102363040267,
"children": {
"process_trajectory": {
"total": 158.72511499011284,
"count": 232760,
"self": 157.31587334011306,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4092416499997853,
"count": 10,
"self": 1.4092416499997853
}
}
},
"_update_policy": {
"total": 327.3218775559983,
"count": 97,
"self": 252.70024011000555,
"children": {
"TorchPPOOptimizer.update": {
"total": 74.62163744599275,
"count": 5820,
"self": 74.62163744599275
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0230000953015406e-06,
"count": 1,
"self": 1.0230000953015406e-06
},
"TrainerController._save_models": {
"total": 0.13373744499995155,
"count": 1,
"self": 0.00272885899994435,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1310085860000072,
"count": 1,
"self": 0.1310085860000072
}
}
}
}
}
}
}