ppo-Huggy / run_logs /timers.json
ANDREEEWW's picture
Huggy
5e38a4c verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4084851741790771,
"min": 1.4084851741790771,
"max": 1.4287208318710327,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70377.78125,
"min": 68917.1796875,
"max": 76954.0859375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 104.67932489451476,
"min": 87.17460317460318,
"max": 407.869918699187,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49618.0,
"min": 48866.0,
"max": 50168.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999998.0,
"min": 49790.0,
"max": 1999998.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999998.0,
"min": 49790.0,
"max": 1999998.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3171072006225586,
"min": 0.25340601801872253,
"max": 2.391758680343628,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1098.308837890625,
"min": 30.91553497314453,
"max": 1331.90771484375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.5820562845795467,
"min": 1.9165250297452583,
"max": 3.883403741003393,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1697.894678890705,
"min": 233.8160536289215,
"max": 2136.3998895287514,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.5820562845795467,
"min": 1.9165250297452583,
"max": 3.883403741003393,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1697.894678890705,
"min": 233.8160536289215,
"max": 2136.3998895287514,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01929384744693784,
"min": 0.01358978096031933,
"max": 0.019671988147698962,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05788154234081352,
"min": 0.02717956192063866,
"max": 0.05901596444309689,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04342383535371886,
"min": 0.020474113834400974,
"max": 0.05959431487652991,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1302715060611566,
"min": 0.04094822766880195,
"max": 0.1787829446295897,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4290988569999927e-06,
"min": 3.4290988569999927e-06,
"max": 0.00029526772657742495,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0287296570999978e-05,
"min": 1.0287296570999978e-05,
"max": 0.0008440284186571999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.101143,
"min": 0.101143,
"max": 0.198422575,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.303429,
"min": 0.2074393,
"max": 0.5813428,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.703569999999991e-05,
"min": 6.703569999999991e-05,
"max": 0.004921286492500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020110709999999972,
"min": 0.00020110709999999972,
"max": 0.014069005720000003,
"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": "1715406393",
"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": "1715408791"
},
"total": 2398.023886303,
"count": 1,
"self": 0.44392849099995146,
"children": {
"run_training.setup": {
"total": 0.05542336199999909,
"count": 1,
"self": 0.05542336199999909
},
"TrainerController.start_learning": {
"total": 2397.52453445,
"count": 1,
"self": 4.191400548861566,
"children": {
"TrainerController._reset_env": {
"total": 3.0505177940000294,
"count": 1,
"self": 3.0505177940000294
},
"TrainerController.advance": {
"total": 2390.167944741139,
"count": 231973,
"self": 4.77702252326344,
"children": {
"env_step": {
"total": 1890.3230618859166,
"count": 231973,
"self": 1564.4992611989842,
"children": {
"SubprocessEnvManager._take_step": {
"total": 323.0000026769725,
"count": 231973,
"self": 16.583394600042766,
"children": {
"TorchPolicy.evaluate": {
"total": 306.4166080769297,
"count": 223088,
"self": 306.4166080769297
}
}
},
"workers": {
"total": 2.8237980099597735,
"count": 231973,
"self": 0.0,
"children": {
"worker_root": {
"total": 2390.384123452946,
"count": 231973,
"is_parallel": true,
"self": 1128.6100712329567,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001199377999967055,
"count": 1,
"is_parallel": true,
"self": 0.0003657929999008047,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008335850000662504,
"count": 2,
"is_parallel": true,
"self": 0.0008335850000662504
}
}
},
"UnityEnvironment.step": {
"total": 0.029029958000023726,
"count": 1,
"is_parallel": true,
"self": 0.00038886500004764457,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022564999994756363,
"count": 1,
"is_parallel": true,
"self": 0.00022564999994756363
},
"communicator.exchange": {
"total": 0.027675894000026346,
"count": 1,
"is_parallel": true,
"self": 0.027675894000026346
},
"steps_from_proto": {
"total": 0.0007395490000021709,
"count": 1,
"is_parallel": true,
"self": 0.0001909910000108539,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000548557999991317,
"count": 2,
"is_parallel": true,
"self": 0.000548557999991317
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1261.7740522199892,
"count": 231972,
"is_parallel": true,
"self": 38.39710640307817,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.03111863595029,
"count": 231972,
"is_parallel": true,
"self": 80.03111863595029
},
"communicator.exchange": {
"total": 1054.5114015309887,
"count": 231972,
"is_parallel": true,
"self": 1054.5114015309887
},
"steps_from_proto": {
"total": 88.83442564997199,
"count": 231972,
"is_parallel": true,
"self": 31.835355519911843,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.99907013006015,
"count": 463944,
"is_parallel": true,
"self": 56.99907013006015
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 495.0678603319588,
"count": 231973,
"self": 6.40568209597069,
"children": {
"process_trajectory": {
"total": 150.77062175898845,
"count": 231973,
"self": 149.15827748398942,
"children": {
"RLTrainer._checkpoint": {
"total": 1.6123442749990318,
"count": 10,
"self": 1.6123442749990318
}
}
},
"_update_policy": {
"total": 337.89155647699965,
"count": 97,
"self": 273.9288318450021,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.96272463199756,
"count": 2910,
"self": 63.96272463199756
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3829999261361081e-06,
"count": 1,
"self": 1.3829999261361081e-06
},
"TrainerController._save_models": {
"total": 0.1146699829996578,
"count": 1,
"self": 0.002076256999771431,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11259372599988637,
"count": 1,
"self": 0.11259372599988637
}
}
}
}
}
}
}