ppo-Huggy / run_logs /timers.json
parallelq's picture
Add Huggy agent to the Hub.
3f49f8c
Raw
History Blame Contribute Delete
17.4 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3991342782974243,
"min": 1.3991342782974243,
"max": 1.4270352125167847,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70207.15625,
"min": 68073.875,
"max": 77440.4609375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 106.28632478632478,
"min": 97.3009900990099,
"max": 378.1503759398496,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49742.0,
"min": 49038.0,
"max": 50294.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999512.0,
"min": 49975.0,
"max": 1999512.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999512.0,
"min": 49975.0,
"max": 1999512.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.415311336517334,
"min": 0.07879433035850525,
"max": 2.415311336517334,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1130.36572265625,
"min": 10.400851249694824,
"max": 1213.13330078125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7984859090075536,
"min": 1.966454240070148,
"max": 3.7984859090075536,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1777.691405415535,
"min": 259.57195968925953,
"max": 1915.8526149988174,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7984859090075536,
"min": 1.966454240070148,
"max": 3.7984859090075536,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1777.691405415535,
"min": 259.57195968925953,
"max": 1915.8526149988174,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01674407451452377,
"min": 0.013527031336794455,
"max": 0.020824601656446853,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03348814902904754,
"min": 0.02705406267358891,
"max": 0.05631858210399514,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0588393767674764,
"min": 0.022886744886636733,
"max": 0.0588393767674764,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1176787535349528,
"min": 0.04577348977327347,
"max": 0.17045243779818217,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.654448448550012e-06,
"min": 4.654448448550012e-06,
"max": 0.00029531985156004996,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.308896897100024e-06,
"min": 9.308896897100024e-06,
"max": 0.0008440458186513998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10155144999999999,
"min": 0.10155144999999999,
"max": 0.19843995000000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20310289999999998,
"min": 0.20310289999999998,
"max": 0.5813486000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.741735500000021e-05,
"min": 8.741735500000021e-05,
"max": 0.0049221535050000004,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00017483471000000043,
"min": 0.00017483471000000043,
"max": 0.01406929514,
"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": "1683403302",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "0.31.0.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": "1683405741"
},
"total": 2438.650981105,
"count": 1,
"self": 0.44324090000009164,
"children": {
"run_training.setup": {
"total": 0.04408445600000732,
"count": 1,
"self": 0.04408445600000732
},
"TrainerController.start_learning": {
"total": 2438.163655749,
"count": 1,
"self": 4.491656299956958,
"children": {
"TrainerController._reset_env": {
"total": 4.058349069999963,
"count": 1,
"self": 4.058349069999963
},
"TrainerController.advance": {
"total": 2429.473210107043,
"count": 230757,
"self": 4.6412573939715,
"children": {
"env_step": {
"total": 1901.33234047701,
"count": 230757,
"self": 1607.902112673073,
"children": {
"SubprocessEnvManager._take_step": {
"total": 290.56621652499723,
"count": 230757,
"self": 17.120384810982728,
"children": {
"TorchPolicy.evaluate": {
"total": 273.4458317140145,
"count": 222947,
"self": 273.4458317140145
}
}
},
"workers": {
"total": 2.864011278939813,
"count": 230757,
"self": 0.0,
"children": {
"worker_root": {
"total": 2430.329669724968,
"count": 230757,
"is_parallel": true,
"self": 1115.0452038589272,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0007113960000424413,
"count": 1,
"is_parallel": true,
"self": 0.00020869900009756748,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005026969999448738,
"count": 2,
"is_parallel": true,
"self": 0.0005026969999448738
}
}
},
"UnityEnvironment.step": {
"total": 0.02853526899997405,
"count": 1,
"is_parallel": true,
"self": 0.0003223819999789157,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020272500000828586,
"count": 1,
"is_parallel": true,
"self": 0.00020272500000828586
},
"communicator.exchange": {
"total": 0.02732083099999727,
"count": 1,
"is_parallel": true,
"self": 0.02732083099999727
},
"steps_from_proto": {
"total": 0.0006893309999895791,
"count": 1,
"is_parallel": true,
"self": 0.00019030100003192274,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004990299999576564,
"count": 2,
"is_parallel": true,
"self": 0.0004990299999576564
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1315.2844658660408,
"count": 230756,
"is_parallel": true,
"self": 39.27259840496731,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.98270995903715,
"count": 230756,
"is_parallel": true,
"self": 78.98270995903715
},
"communicator.exchange": {
"total": 1102.277931863025,
"count": 230756,
"is_parallel": true,
"self": 1102.277931863025
},
"steps_from_proto": {
"total": 94.75122563901147,
"count": 230756,
"is_parallel": true,
"self": 33.86742337708165,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.883802261929816,
"count": 461512,
"is_parallel": true,
"self": 60.883802261929816
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 523.4996122360618,
"count": 230757,
"self": 7.195632625094845,
"children": {
"process_trajectory": {
"total": 131.22164284696726,
"count": 230757,
"self": 129.8986988339674,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3229440129998693,
"count": 10,
"self": 1.3229440129998693
}
}
},
"_update_policy": {
"total": 385.08233676399976,
"count": 96,
"self": 324.5001169529979,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.582219811001835,
"count": 2880,
"self": 60.582219811001835
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0280000424245372e-06,
"count": 1,
"self": 1.0280000424245372e-06
},
"TrainerController._save_models": {
"total": 0.14043924399993557,
"count": 1,
"self": 0.002380868999807717,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13805837500012785,
"count": 1,
"self": 0.13805837500012785
}
}
}
}
}
}
}