ppo-Huggy / run_logs /timers.json
cauaveiga's picture
Huggy
4395d29 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4080698490142822,
"min": 1.4080698490142822,
"max": 1.4294636249542236,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69909.2578125,
"min": 69286.6953125,
"max": 78044.078125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 90.1524500907441,
"min": 74.54211332312404,
"max": 387.7984496124031,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49674.0,
"min": 48676.0,
"max": 50026.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999523.0,
"min": 49481.0,
"max": 1999523.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999523.0,
"min": 49481.0,
"max": 1999523.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4368412494659424,
"min": 0.06684580445289612,
"max": 2.4921891689300537,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1342.699462890625,
"min": 8.556262969970703,
"max": 1603.0706787109375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7297724653069206,
"min": 1.722673777025193,
"max": 4.001449506105103,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2055.1046283841133,
"min": 220.5022434592247,
"max": 2576.9334819316864,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7297724653069206,
"min": 1.722673777025193,
"max": 4.001449506105103,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2055.1046283841133,
"min": 220.5022434592247,
"max": 2576.9334819316864,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018179118146852285,
"min": 0.013326068420307516,
"max": 0.01905477426989819,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05453735444055686,
"min": 0.026652136840615032,
"max": 0.05548589892374973,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04967090168760882,
"min": 0.022515438745419183,
"max": 0.06940815361837546,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14901270506282646,
"min": 0.04503087749083837,
"max": 0.18618859524528186,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.808548730516662e-06,
"min": 3.808548730516662e-06,
"max": 0.000295320376559875,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1425646191549986e-05,
"min": 1.1425646191549986e-05,
"max": 0.00084415666861445,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10126948333333334,
"min": 0.10126948333333334,
"max": 0.19844012499999997,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30380845,
"min": 0.20768660000000005,
"max": 0.58138555,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.334721833333328e-05,
"min": 7.334721833333328e-05,
"max": 0.004922162237500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022004165499999983,
"min": 0.00022004165499999983,
"max": 0.014071138944999999,
"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": "1722166625",
"python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1722169027"
},
"total": 2402.0393773690002,
"count": 1,
"self": 0.48721404200023244,
"children": {
"run_training.setup": {
"total": 0.0899589760000481,
"count": 1,
"self": 0.0899589760000481
},
"TrainerController.start_learning": {
"total": 2401.462204351,
"count": 1,
"self": 4.371763217016451,
"children": {
"TrainerController._reset_env": {
"total": 3.1644646580000426,
"count": 1,
"self": 3.1644646580000426
},
"TrainerController.advance": {
"total": 2393.811675617983,
"count": 232900,
"self": 4.6106807359497,
"children": {
"env_step": {
"total": 1898.687351164993,
"count": 232900,
"self": 1563.280058673944,
"children": {
"SubprocessEnvManager._take_step": {
"total": 332.5619539390433,
"count": 232900,
"self": 17.27667270710276,
"children": {
"TorchPolicy.evaluate": {
"total": 315.28528123194053,
"count": 222968,
"self": 315.28528123194053
}
}
},
"workers": {
"total": 2.8453385520056145,
"count": 232900,
"self": 0.0,
"children": {
"worker_root": {
"total": 2394.230441198051,
"count": 232900,
"is_parallel": true,
"self": 1134.8686582651135,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001166892000014741,
"count": 1,
"is_parallel": true,
"self": 0.0002852060000577694,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008816859999569715,
"count": 2,
"is_parallel": true,
"self": 0.0008816859999569715
}
}
},
"UnityEnvironment.step": {
"total": 0.029717551999965508,
"count": 1,
"is_parallel": true,
"self": 0.00040616700005102757,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022804499997164385,
"count": 1,
"is_parallel": true,
"self": 0.00022804499997164385
},
"communicator.exchange": {
"total": 0.028287571999953798,
"count": 1,
"is_parallel": true,
"self": 0.028287571999953798
},
"steps_from_proto": {
"total": 0.0007957679999890388,
"count": 1,
"is_parallel": true,
"self": 0.00023978799993074063,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005559800000582982,
"count": 2,
"is_parallel": true,
"self": 0.0005559800000582982
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1259.3617829329373,
"count": 232899,
"is_parallel": true,
"self": 38.49819160295874,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.68047888593549,
"count": 232899,
"is_parallel": true,
"self": 82.68047888593549
},
"communicator.exchange": {
"total": 1046.0562658659858,
"count": 232899,
"is_parallel": true,
"self": 1046.0562658659858
},
"steps_from_proto": {
"total": 92.12684657805721,
"count": 232899,
"is_parallel": true,
"self": 34.54325136517252,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.58359521288469,
"count": 465798,
"is_parallel": true,
"self": 57.58359521288469
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 490.5136437170404,
"count": 232900,
"self": 6.449211743051251,
"children": {
"process_trajectory": {
"total": 156.05989187199054,
"count": 232900,
"self": 154.6574628179893,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4024290540012316,
"count": 10,
"self": 1.4024290540012316
}
}
},
"_update_policy": {
"total": 328.0045401019986,
"count": 97,
"self": 265.02786996899874,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.97667013299986,
"count": 2910,
"self": 62.97667013299986
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1050001376133878e-06,
"count": 1,
"self": 1.1050001376133878e-06
},
"TrainerController._save_models": {
"total": 0.11429975300006845,
"count": 1,
"self": 0.0019173119999322807,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11238244100013617,
"count": 1,
"self": 0.11238244100013617
}
}
}
}
}
}
}