ppo-Huggy / run_logs /timers.json
jcramirezpr's picture
huggy bonus unit 1
2e8274e
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4112669229507446,
"min": 1.4112669229507446,
"max": 1.4305262565612793,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71132.0859375,
"min": 69504.796875,
"max": 77373.0546875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 75.13373860182371,
"min": 74.57639939485628,
"max": 364.05839416058393,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49438.0,
"min": 49045.0,
"max": 49967.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999354.0,
"min": 49773.0,
"max": 1999354.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999354.0,
"min": 49773.0,
"max": 1999354.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.513890266418457,
"min": 0.08426234871149063,
"max": 2.513890266418457,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1654.1397705078125,
"min": 11.45967960357666,
"max": 1654.1397705078125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.859367948806757,
"min": 1.7746019556241877,
"max": 3.945694402853648,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2539.464110314846,
"min": 241.34586596488953,
"max": 2539.464110314846,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.859367948806757,
"min": 1.7746019556241877,
"max": 3.945694402853648,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2539.464110314846,
"min": 241.34586596488953,
"max": 2539.464110314846,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017513285818859,
"min": 0.013530004894710145,
"max": 0.021482121614584078,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05253985745657701,
"min": 0.028095774666871874,
"max": 0.059515248473083676,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06269641539288891,
"min": 0.022654564399272204,
"max": 0.06460776024808486,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18808924617866674,
"min": 0.04530912879854441,
"max": 0.18808924617866674,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.794148735316672e-06,
"min": 3.794148735316672e-06,
"max": 0.0002953485015505,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1382446205950015e-05,
"min": 1.1382446205950015e-05,
"max": 0.0008442781685739499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10126468333333331,
"min": 0.10126468333333331,
"max": 0.19844949999999995,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3037940499999999,
"min": 0.2076672,
"max": 0.5814260500000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.310769833333341e-05,
"min": 7.310769833333341e-05,
"max": 0.0049226300500000006,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021932309500000024,
"min": 0.00021932309500000024,
"max": 0.014073159895000003,
"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": "1676645293",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1676647823"
},
"total": 2530.0966481610003,
"count": 1,
"self": 0.447812246000467,
"children": {
"run_training.setup": {
"total": 0.12733989100001963,
"count": 1,
"self": 0.12733989100001963
},
"TrainerController.start_learning": {
"total": 2529.521496024,
"count": 1,
"self": 4.6926527390992305,
"children": {
"TrainerController._reset_env": {
"total": 10.93257307600004,
"count": 1,
"self": 10.93257307600004
},
"TrainerController.advance": {
"total": 2513.7760267029003,
"count": 232753,
"self": 4.820760535940735,
"children": {
"env_step": {
"total": 1977.2516460820307,
"count": 232753,
"self": 1647.5649887730056,
"children": {
"SubprocessEnvManager._take_step": {
"total": 326.6514896160602,
"count": 232753,
"self": 16.88440676798973,
"children": {
"TorchPolicy.evaluate": {
"total": 309.76708284807046,
"count": 222928,
"self": 77.26236870122534,
"children": {
"TorchPolicy.sample_actions": {
"total": 232.50471414684512,
"count": 222928,
"self": 232.50471414684512
}
}
}
}
},
"workers": {
"total": 3.0351676929650466,
"count": 232753,
"self": 0.0,
"children": {
"worker_root": {
"total": 2520.1572148669834,
"count": 232753,
"is_parallel": true,
"self": 1186.7491990219646,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001996101000031558,
"count": 1,
"is_parallel": true,
"self": 0.00040109400003984774,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015950069999917105,
"count": 2,
"is_parallel": true,
"self": 0.0015950069999917105
}
}
},
"UnityEnvironment.step": {
"total": 0.03330210499996156,
"count": 1,
"is_parallel": true,
"self": 0.0003677050000305826,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022104200002104335,
"count": 1,
"is_parallel": true,
"self": 0.00022104200002104335
},
"communicator.exchange": {
"total": 0.03193213800000194,
"count": 1,
"is_parallel": true,
"self": 0.03193213800000194
},
"steps_from_proto": {
"total": 0.0007812199999079894,
"count": 1,
"is_parallel": true,
"self": 0.0002793429999883301,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005018769999196593,
"count": 2,
"is_parallel": true,
"self": 0.0005018769999196593
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1333.4080158450188,
"count": 232752,
"is_parallel": true,
"self": 40.45263364413222,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.1823054729715,
"count": 232752,
"is_parallel": true,
"self": 84.1823054729715
},
"communicator.exchange": {
"total": 1108.9764842799505,
"count": 232752,
"is_parallel": true,
"self": 1108.9764842799505
},
"steps_from_proto": {
"total": 99.79659244796449,
"count": 232752,
"is_parallel": true,
"self": 42.40930183803334,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.38729060993114,
"count": 465504,
"is_parallel": true,
"self": 57.38729060993114
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 531.703620084929,
"count": 232753,
"self": 7.047651431995632,
"children": {
"process_trajectory": {
"total": 171.86639414793183,
"count": 232753,
"self": 170.68227235493157,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1841217930002585,
"count": 10,
"self": 1.1841217930002585
}
}
},
"_update_policy": {
"total": 352.7895745050015,
"count": 97,
"self": 295.2021925010075,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.58738200399398,
"count": 2910,
"self": 57.58738200399398
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.360002539120615e-07,
"count": 1,
"self": 8.360002539120615e-07
},
"TrainerController._save_models": {
"total": 0.12024267000015243,
"count": 1,
"self": 0.00200343000005887,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11823924000009356,
"count": 1,
"self": 0.11823924000009356
}
}
}
}
}
}
}