ppo-Huggy / run_logs /timers.json
jarski's picture
My first Huggy
7f54d8c verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4016077518463135,
"min": 1.4016077518463135,
"max": 1.4279963970184326,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69201.578125,
"min": 68978.78125,
"max": 76720.1796875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 71.52173913043478,
"min": 68.86573426573426,
"max": 394.0551181102362,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49350.0,
"min": 48899.0,
"max": 50136.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999989.0,
"min": 49623.0,
"max": 1999989.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999989.0,
"min": 49623.0,
"max": 1999989.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.487297296524048,
"min": 0.10801764577627182,
"max": 2.5401012897491455,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1716.235107421875,
"min": 13.610223770141602,
"max": 1802.822021484375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8679365187451458,
"min": 1.898877593378226,
"max": 4.124186505325909,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2668.8761979341507,
"min": 239.25857676565647,
"max": 2780.4843205213547,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8679365187451458,
"min": 1.898877593378226,
"max": 4.124186505325909,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2668.8761979341507,
"min": 239.25857676565647,
"max": 2780.4843205213547,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01786194866031615,
"min": 0.013565646266700544,
"max": 0.01975995525410023,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.053585845980948454,
"min": 0.02713129253340109,
"max": 0.05695481028912279,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06378788016736507,
"min": 0.0222878137913843,
"max": 0.06378788016736507,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.19136364050209523,
"min": 0.0445756275827686,
"max": 0.19136364050209523,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.953698682133336e-06,
"min": 3.953698682133336e-06,
"max": 0.00029530732656422496,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1861096046400007e-05,
"min": 1.1861096046400007e-05,
"max": 0.0008440773186408997,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10131786666666669,
"min": 0.10131786666666669,
"max": 0.19843577500000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30395360000000005,
"min": 0.20778290000000005,
"max": 0.5813591000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.576154666666668e-05,
"min": 7.576154666666668e-05,
"max": 0.004921945172500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022728464000000006,
"min": 0.00022728464000000006,
"max": 0.014069819090000001,
"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": "1717149525",
"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=MyHuggy --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1717151999"
},
"total": 2474.8135342739997,
"count": 1,
"self": 0.4732039449995682,
"children": {
"run_training.setup": {
"total": 0.06172472800005835,
"count": 1,
"self": 0.06172472800005835
},
"TrainerController.start_learning": {
"total": 2474.278605601,
"count": 1,
"self": 4.730194005026078,
"children": {
"TrainerController._reset_env": {
"total": 3.7829910940000673,
"count": 1,
"self": 3.7829910940000673
},
"TrainerController.advance": {
"total": 2465.648578782974,
"count": 233541,
"self": 4.7740706800036605,
"children": {
"env_step": {
"total": 1942.2022093959736,
"count": 233541,
"self": 1604.139205415005,
"children": {
"SubprocessEnvManager._take_step": {
"total": 335.13061458189736,
"count": 233541,
"self": 17.06931974793372,
"children": {
"TorchPolicy.evaluate": {
"total": 318.06129483396364,
"count": 222871,
"self": 318.06129483396364
}
}
},
"workers": {
"total": 2.932389399071212,
"count": 233541,
"self": 0.0,
"children": {
"worker_root": {
"total": 2466.8649314239947,
"count": 233541,
"is_parallel": true,
"self": 1174.1897260500823,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011075410000103147,
"count": 1,
"is_parallel": true,
"self": 0.0002672370000027513,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008403040000075634,
"count": 2,
"is_parallel": true,
"self": 0.0008403040000075634
}
}
},
"UnityEnvironment.step": {
"total": 0.04055633099994793,
"count": 1,
"is_parallel": true,
"self": 0.00039214999992509547,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019660899999962567,
"count": 1,
"is_parallel": true,
"self": 0.00019660899999962567
},
"communicator.exchange": {
"total": 0.03920320999998239,
"count": 1,
"is_parallel": true,
"self": 0.03920320999998239
},
"steps_from_proto": {
"total": 0.0007643620000408191,
"count": 1,
"is_parallel": true,
"self": 0.00023006099991107476,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005343010001297444,
"count": 2,
"is_parallel": true,
"self": 0.0005343010001297444
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1292.6752053739124,
"count": 233540,
"is_parallel": true,
"self": 40.077679290840024,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.75454447305708,
"count": 233540,
"is_parallel": true,
"self": 82.75454447305708
},
"communicator.exchange": {
"total": 1077.5061043630562,
"count": 233540,
"is_parallel": true,
"self": 1077.5061043630562
},
"steps_from_proto": {
"total": 92.33687724695903,
"count": 233540,
"is_parallel": true,
"self": 32.860677274824866,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.47619997213417,
"count": 467080,
"is_parallel": true,
"self": 59.47619997213417
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 518.6722987069966,
"count": 233541,
"self": 6.797038085920917,
"children": {
"process_trajectory": {
"total": 167.33144009507646,
"count": 233541,
"self": 165.95613789307595,
"children": {
"RLTrainer._checkpoint": {
"total": 1.375302202000512,
"count": 10,
"self": 1.375302202000512
}
}
},
"_update_policy": {
"total": 344.5438205259992,
"count": 97,
"self": 279.16392284000824,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.37989768599095,
"count": 2910,
"self": 65.37989768599095
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4199999895936344e-06,
"count": 1,
"self": 1.4199999895936344e-06
},
"TrainerController._save_models": {
"total": 0.11684029900015958,
"count": 1,
"self": 0.002881148000142275,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1139591510000173,
"count": 1,
"self": 0.1139591510000173
}
}
}
}
}
}
}