ppo-Huggy / run_logs /timers.json
Snorlax's picture
Huggy
300b379 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4036794900894165,
"min": 1.4036794900894165,
"max": 1.4282547235488892,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69409.140625,
"min": 68688.7734375,
"max": 78247.46875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 98.04554455445545,
"min": 93.25471698113208,
"max": 364.72463768115944,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49513.0,
"min": 49154.0,
"max": 50332.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999963.0,
"min": 49720.0,
"max": 1999963.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999963.0,
"min": 49720.0,
"max": 1999963.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.380131721496582,
"min": 0.07056697458028793,
"max": 2.4174182415008545,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1201.966552734375,
"min": 9.667675018310547,
"max": 1265.5166015625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.761439509557025,
"min": 1.9584928785797453,
"max": 3.9270124703959417,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1899.5269523262978,
"min": 268.3135243654251,
"max": 1963.0380450487137,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.761439509557025,
"min": 1.9584928785797453,
"max": 3.9270124703959417,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1899.5269523262978,
"min": 268.3135243654251,
"max": 1963.0380450487137,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015483770890447585,
"min": 0.01400210906455565,
"max": 0.020925646243752757,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.046451312671342754,
"min": 0.0280042181291113,
"max": 0.06277693873125827,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05387544971373346,
"min": 0.022737291144828004,
"max": 0.05528003262976805,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1616263491412004,
"min": 0.04547458228965601,
"max": 0.1616263491412004,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5060988313333315e-06,
"min": 3.5060988313333315e-06,
"max": 0.0002953831515389501,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0518296493999994e-05,
"min": 1.0518296493999994e-05,
"max": 0.0008441763186078997,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10116866666666667,
"min": 0.10116866666666667,
"max": 0.19846105000000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.303506,
"min": 0.20749280000000006,
"max": 0.5813921000000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.831646666666663e-05,
"min": 6.831646666666663e-05,
"max": 0.004923206395000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020494939999999987,
"min": 0.00020494939999999987,
"max": 0.014071465790000003,
"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": "1732541826",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1732544152"
},
"total": 2325.956806342,
"count": 1,
"self": 0.6629117600000427,
"children": {
"run_training.setup": {
"total": 0.05599523999990197,
"count": 1,
"self": 0.05599523999990197
},
"TrainerController.start_learning": {
"total": 2325.237899342,
"count": 1,
"self": 4.145575680015554,
"children": {
"TrainerController._reset_env": {
"total": 5.8804314230000045,
"count": 1,
"self": 5.8804314230000045
},
"TrainerController.advance": {
"total": 2315.0502456249847,
"count": 231426,
"self": 4.195043841004008,
"children": {
"env_step": {
"total": 1826.142513422062,
"count": 231426,
"self": 1429.5385458779206,
"children": {
"SubprocessEnvManager._take_step": {
"total": 393.96352872406214,
"count": 231426,
"self": 15.17665677215848,
"children": {
"TorchPolicy.evaluate": {
"total": 378.78687195190366,
"count": 222888,
"self": 378.78687195190366
}
}
},
"workers": {
"total": 2.640438820079339,
"count": 231426,
"self": 0.0,
"children": {
"worker_root": {
"total": 2318.4444476729564,
"count": 231426,
"is_parallel": true,
"self": 1156.1202212799062,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000964866999993319,
"count": 1,
"is_parallel": true,
"self": 0.0002935649998789813,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006713020001143377,
"count": 2,
"is_parallel": true,
"self": 0.0006713020001143377
}
}
},
"UnityEnvironment.step": {
"total": 0.02834282300000268,
"count": 1,
"is_parallel": true,
"self": 0.00036468700011482724,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021606399991469516,
"count": 1,
"is_parallel": true,
"self": 0.00021606399991469516
},
"communicator.exchange": {
"total": 0.027034533000005467,
"count": 1,
"is_parallel": true,
"self": 0.027034533000005467
},
"steps_from_proto": {
"total": 0.0007275389999676918,
"count": 1,
"is_parallel": true,
"self": 0.00019601499991495075,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000531524000052741,
"count": 2,
"is_parallel": true,
"self": 0.000531524000052741
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1162.3242263930501,
"count": 231425,
"is_parallel": true,
"self": 35.96930101916655,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.86143751993916,
"count": 231425,
"is_parallel": true,
"self": 78.86143751993916
},
"communicator.exchange": {
"total": 962.8131209940628,
"count": 231425,
"is_parallel": true,
"self": 962.8131209940628
},
"steps_from_proto": {
"total": 84.68036685988159,
"count": 231425,
"is_parallel": true,
"self": 29.9932903729092,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.68707648697239,
"count": 462850,
"is_parallel": true,
"self": 54.68707648697239
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 484.7126883619186,
"count": 231426,
"self": 5.916235867902856,
"children": {
"process_trajectory": {
"total": 155.60451706701554,
"count": 231426,
"self": 154.166738549015,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4377785180005276,
"count": 10,
"self": 1.4377785180005276
}
}
},
"_update_policy": {
"total": 323.1919354270002,
"count": 97,
"self": 257.97234328600007,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.21959214100013,
"count": 2910,
"self": 65.21959214100013
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2579998838191386e-06,
"count": 1,
"self": 1.2579998838191386e-06
},
"TrainerController._save_models": {
"total": 0.16164535600000818,
"count": 1,
"self": 0.003146830999867234,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15849852500014094,
"count": 1,
"self": 0.15849852500014094
}
}
}
}
}
}
}