ppo-MaddyHuggy / run_logs /timers.json
Sanyam0605's picture
Maddy - the real huggy
cb2d70e
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.404541015625,
"min": 1.404541015625,
"max": 1.4286199808120728,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70600.65625,
"min": 68202.0,
"max": 76549.0390625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 88.91592128801432,
"min": 85.85069444444444,
"max": 380.43939393939394,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49704.0,
"min": 48813.0,
"max": 50218.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999829.0,
"min": 49601.0,
"max": 1999829.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999829.0,
"min": 49601.0,
"max": 1999829.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.437941074371338,
"min": 0.01884124055504799,
"max": 2.4604134559631348,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1360.37109375,
"min": 2.468202590942383,
"max": 1389.80419921875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7984079069134156,
"min": 1.787016050051187,
"max": 3.918041879458553,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2119.511612057686,
"min": 234.09910255670547,
"max": 2150.34184640646,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7984079069134156,
"min": 1.787016050051187,
"max": 3.918041879458553,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2119.511612057686,
"min": 234.09910255670547,
"max": 2150.34184640646,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01641533482761588,
"min": 0.014666735183507425,
"max": 0.020396181303173458,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04924600448284763,
"min": 0.02982179233841483,
"max": 0.059343468939187,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05584721287919416,
"min": 0.02375201437001427,
"max": 0.05584721287919416,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16754163863758248,
"min": 0.04750402874002854,
"max": 0.16754163863758248,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.321598892833332e-06,
"min": 3.321598892833332e-06,
"max": 0.00029528070157309994,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.964796678499997e-06,
"min": 9.964796678499997e-06,
"max": 0.0008439720186759999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10110716666666668,
"min": 0.10110716666666668,
"max": 0.19842690000000007,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3033215,
"min": 0.2073619,
"max": 0.5813240000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.524761666666667e-05,
"min": 6.524761666666667e-05,
"max": 0.004921502309999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019574285000000002,
"min": 0.00019574285000000002,
"max": 0.014068067600000001,
"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": "1694905172",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1694907802"
},
"total": 2629.320578841,
"count": 1,
"self": 0.4370878009999615,
"children": {
"run_training.setup": {
"total": 0.07609936799997286,
"count": 1,
"self": 0.07609936799997286
},
"TrainerController.start_learning": {
"total": 2628.807391672,
"count": 1,
"self": 4.999313134025215,
"children": {
"TrainerController._reset_env": {
"total": 4.84070589800001,
"count": 1,
"self": 4.84070589800001
},
"TrainerController.advance": {
"total": 2618.8383356729746,
"count": 231926,
"self": 4.964045135033302,
"children": {
"env_step": {
"total": 2016.4162382639436,
"count": 231926,
"self": 1702.3380516659217,
"children": {
"SubprocessEnvManager._take_step": {
"total": 310.8953661199545,
"count": 231926,
"self": 17.961502292967452,
"children": {
"TorchPolicy.evaluate": {
"total": 292.933863826987,
"count": 222938,
"self": 292.933863826987
}
}
},
"workers": {
"total": 3.182820478067242,
"count": 231926,
"self": 0.0,
"children": {
"worker_root": {
"total": 2620.8091350550376,
"count": 231926,
"is_parallel": true,
"self": 1232.5291175739108,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0013804510000454684,
"count": 1,
"is_parallel": true,
"self": 0.000519207000024835,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008612440000206334,
"count": 2,
"is_parallel": true,
"self": 0.0008612440000206334
}
}
},
"UnityEnvironment.step": {
"total": 0.030859850999945593,
"count": 1,
"is_parallel": true,
"self": 0.00035127199998896685,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002396309999994628,
"count": 1,
"is_parallel": true,
"self": 0.0002396309999994628
},
"communicator.exchange": {
"total": 0.02946205099999588,
"count": 1,
"is_parallel": true,
"self": 0.02946205099999588
},
"steps_from_proto": {
"total": 0.0008068969999612818,
"count": 1,
"is_parallel": true,
"self": 0.00023426200004905695,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005726349999122249,
"count": 2,
"is_parallel": true,
"self": 0.0005726349999122249
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1388.2800174811268,
"count": 231925,
"is_parallel": true,
"self": 42.985200280153094,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 85.71188899997048,
"count": 231925,
"is_parallel": true,
"self": 85.71188899997048
},
"communicator.exchange": {
"total": 1155.1442604320027,
"count": 231925,
"is_parallel": true,
"self": 1155.1442604320027
},
"steps_from_proto": {
"total": 104.4386677690004,
"count": 231925,
"is_parallel": true,
"self": 37.0750142148778,
"children": {
"_process_rank_one_or_two_observation": {
"total": 67.3636535541226,
"count": 463850,
"is_parallel": true,
"self": 67.3636535541226
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 597.4580522739976,
"count": 231926,
"self": 7.273692354841046,
"children": {
"process_trajectory": {
"total": 145.99305437415603,
"count": 231926,
"self": 144.40893190615623,
"children": {
"RLTrainer._checkpoint": {
"total": 1.584122467999805,
"count": 10,
"self": 1.584122467999805
}
}
},
"_update_policy": {
"total": 444.19130554500055,
"count": 97,
"self": 381.0351562530019,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.156149291998645,
"count": 2910,
"self": 63.156149291998645
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.780001164472196e-07,
"count": 1,
"self": 9.780001164472196e-07
},
"TrainerController._save_models": {
"total": 0.12903598899993085,
"count": 1,
"self": 0.0024947160000010626,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1265412729999298,
"count": 1,
"self": 0.1265412729999298
}
}
}
}
}
}
}