ppo-Huggy / run_logs /timers.json
albertzuo's picture
Huggy
05ca2be verified
raw
history blame
17.4 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4023818969726562,
"min": 1.4023818969726562,
"max": 1.4261517524719238,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70169.578125,
"min": 68658.484375,
"max": 78545.859375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 108.78021978021978,
"min": 94.87332053742803,
"max": 424.89830508474574,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49495.0,
"min": 48898.0,
"max": 50138.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999962.0,
"min": 49506.0,
"max": 1999962.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999962.0,
"min": 49506.0,
"max": 1999962.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.314380645751953,
"min": 0.16223084926605225,
"max": 2.3965110778808594,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1053.043212890625,
"min": 18.981008529663086,
"max": 1207.6611328125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.5691596898403795,
"min": 1.8232879074465516,
"max": 3.8850289390618573,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1623.9676588773727,
"min": 213.32468517124653,
"max": 1899.7791512012482,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.5691596898403795,
"min": 1.8232879074465516,
"max": 3.8850289390618573,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1623.9676588773727,
"min": 213.32468517124653,
"max": 1899.7791512012482,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.020502153281267966,
"min": 0.013341510237660259,
"max": 0.020502153281267966,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04100430656253593,
"min": 0.02721049294341356,
"max": 0.0555502445892974,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04512708888699611,
"min": 0.019941339765985805,
"max": 0.05286075143764417,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.09025417777399222,
"min": 0.03988267953197161,
"max": 0.15294898748397825,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.554398481900001e-06,
"min": 4.554398481900001e-06,
"max": 0.00029535975154675005,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.108796963800002e-06,
"min": 9.108796963800002e-06,
"max": 0.0008441413686195499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10151809999999997,
"min": 0.10151809999999997,
"max": 0.19845325000000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20303619999999994,
"min": 0.20303619999999994,
"max": 0.58138045,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.575318999999999e-05,
"min": 8.575318999999999e-05,
"max": 0.004922817175,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00017150637999999998,
"min": 0.00017150637999999998,
"max": 0.014070884454999998,
"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": "1727858127",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1727860678"
},
"total": 2551.133872875,
"count": 1,
"self": 0.7551431430001685,
"children": {
"run_training.setup": {
"total": 0.057176878000007036,
"count": 1,
"self": 0.057176878000007036
},
"TrainerController.start_learning": {
"total": 2550.321552854,
"count": 1,
"self": 4.554287367958295,
"children": {
"TrainerController._reset_env": {
"total": 2.774158064000005,
"count": 1,
"self": 2.774158064000005
},
"TrainerController.advance": {
"total": 2542.809973073042,
"count": 231750,
"self": 4.6322149899456235,
"children": {
"env_step": {
"total": 2016.635457534005,
"count": 231750,
"self": 1592.6904892071225,
"children": {
"SubprocessEnvManager._take_step": {
"total": 421.062581242932,
"count": 231750,
"self": 15.775696277828104,
"children": {
"TorchPolicy.evaluate": {
"total": 405.2868849651039,
"count": 223050,
"self": 405.2868849651039
}
}
},
"workers": {
"total": 2.882387083950391,
"count": 231750,
"self": 0.0,
"children": {
"worker_root": {
"total": 2542.791279801029,
"count": 231750,
"is_parallel": true,
"self": 1249.9983167070152,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010448620000147457,
"count": 1,
"is_parallel": true,
"self": 0.0003154070000164211,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007294549999983246,
"count": 2,
"is_parallel": true,
"self": 0.0007294549999983246
}
}
},
"UnityEnvironment.step": {
"total": 0.0688006099999825,
"count": 1,
"is_parallel": true,
"self": 0.00040111299995260197,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002087810000261925,
"count": 1,
"is_parallel": true,
"self": 0.0002087810000261925
},
"communicator.exchange": {
"total": 0.06742873299998564,
"count": 1,
"is_parallel": true,
"self": 0.06742873299998564
},
"steps_from_proto": {
"total": 0.0007619830000180627,
"count": 1,
"is_parallel": true,
"self": 0.00018882400001984934,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005731589999982134,
"count": 2,
"is_parallel": true,
"self": 0.0005731589999982134
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1292.7929630940137,
"count": 231749,
"is_parallel": true,
"self": 39.21574952107812,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.32683809294139,
"count": 231749,
"is_parallel": true,
"self": 84.32683809294139
},
"communicator.exchange": {
"total": 1077.585886001944,
"count": 231749,
"is_parallel": true,
"self": 1077.585886001944
},
"steps_from_proto": {
"total": 91.66448947805014,
"count": 231749,
"is_parallel": true,
"self": 32.85182975994684,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.812659718103305,
"count": 463498,
"is_parallel": true,
"self": 58.812659718103305
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 521.5423005490914,
"count": 231750,
"self": 6.640302897053175,
"children": {
"process_trajectory": {
"total": 163.04000664903845,
"count": 231750,
"self": 161.50057933803907,
"children": {
"RLTrainer._checkpoint": {
"total": 1.539427310999372,
"count": 10,
"self": 1.539427310999372
}
}
},
"_update_policy": {
"total": 351.86199100299973,
"count": 96,
"self": 282.83081857899845,
"children": {
"TorchPPOOptimizer.update": {
"total": 69.03117242400128,
"count": 2880,
"self": 69.03117242400128
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.5189998521236703e-06,
"count": 1,
"self": 1.5189998521236703e-06
},
"TrainerController._save_models": {
"total": 0.18313282999997682,
"count": 1,
"self": 0.0028592509997906745,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18027357900018615,
"count": 1,
"self": 0.18027357900018615
}
}
}
}
}
}
}