ppo-Huggy / run_logs /timers.json
ChihoonLee3's picture
Huggy
e288548 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.412933588027954,
"min": 1.412933588027954,
"max": 1.4326127767562866,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70400.828125,
"min": 67818.953125,
"max": 78057.78125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 87.91754385964913,
"min": 82.32,
"max": 397.62698412698415,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 50113.0,
"min": 48904.0,
"max": 50113.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999980.0,
"min": 49816.0,
"max": 1999980.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999980.0,
"min": 49816.0,
"max": 1999980.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.462637424468994,
"min": 0.05468456819653511,
"max": 2.4933130741119385,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1403.703369140625,
"min": 6.835570812225342,
"max": 1478.891357421875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.793727905813016,
"min": 1.8482525815963746,
"max": 4.033170955550731,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2162.4249063134193,
"min": 231.0315726995468,
"max": 2367.4713509082794,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.793727905813016,
"min": 1.8482525815963746,
"max": 4.033170955550731,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2162.4249063134193,
"min": 231.0315726995468,
"max": 2367.4713509082794,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017095633648568767,
"min": 0.010965769448375795,
"max": 0.02005148790582704,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0512869009457063,
"min": 0.02193153889675159,
"max": 0.06015446371748112,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.054820359705222976,
"min": 0.02236792981210682,
"max": 0.060834515529374286,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16446107911566893,
"min": 0.04516446068882942,
"max": 0.17381852939724923,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5593988135666646e-06,
"min": 3.5593988135666646e-06,
"max": 0.0002953343265552249,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0678196440699993e-05,
"min": 1.0678196440699993e-05,
"max": 0.0008441730186089999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10118643333333333,
"min": 0.10118643333333333,
"max": 0.19844477500000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3035593,
"min": 0.20754129999999998,
"max": 0.5813910000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.920302333333331e-05,
"min": 6.920302333333331e-05,
"max": 0.004922394272499998,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020760906999999992,
"min": 0.00020760906999999992,
"max": 0.014071410900000001,
"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": "1739648806",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics --resume",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1739651188"
},
"total": 2382.083131134,
"count": 1,
"self": 0.716584645999319,
"children": {
"run_training.setup": {
"total": 0.020834044000366703,
"count": 1,
"self": 0.020834044000366703
},
"TrainerController.start_learning": {
"total": 2381.345712444,
"count": 1,
"self": 4.205491898911532,
"children": {
"TrainerController._reset_env": {
"total": 2.0608898919999774,
"count": 1,
"self": 2.0608898919999774
},
"TrainerController.advance": {
"total": 2374.8937139580885,
"count": 232398,
"self": 4.1575509848617,
"children": {
"env_step": {
"total": 1877.7571544487118,
"count": 232398,
"self": 1465.1871841752618,
"children": {
"SubprocessEnvManager._take_step": {
"total": 410.0554467970269,
"count": 232398,
"self": 15.128672563594591,
"children": {
"TorchPolicy.evaluate": {
"total": 394.9267742334323,
"count": 222961,
"self": 394.9267742334323
}
}
},
"workers": {
"total": 2.5145234764231645,
"count": 232398,
"self": 0.0,
"children": {
"worker_root": {
"total": 2374.0582744678277,
"count": 232398,
"is_parallel": true,
"self": 1178.0587734649253,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008869600005709799,
"count": 1,
"is_parallel": true,
"self": 0.0002217110004494316,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006652490001215483,
"count": 2,
"is_parallel": true,
"self": 0.0006652490001215483
}
}
},
"UnityEnvironment.step": {
"total": 0.052748355000403535,
"count": 1,
"is_parallel": true,
"self": 0.0004951480004820041,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001720769996609306,
"count": 1,
"is_parallel": true,
"self": 0.0001720769996609306
},
"communicator.exchange": {
"total": 0.0508761040000536,
"count": 1,
"is_parallel": true,
"self": 0.0508761040000536
},
"steps_from_proto": {
"total": 0.001205026000206999,
"count": 1,
"is_parallel": true,
"self": 0.0003004000009241281,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009046259992828709,
"count": 2,
"is_parallel": true,
"self": 0.0009046259992828709
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1195.9995010029024,
"count": 232397,
"is_parallel": true,
"self": 35.95916149027653,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.01562818316233,
"count": 232397,
"is_parallel": true,
"self": 79.01562818316233
},
"communicator.exchange": {
"total": 996.8322958122526,
"count": 232397,
"is_parallel": true,
"self": 996.8322958122526
},
"steps_from_proto": {
"total": 84.19241551721097,
"count": 232397,
"is_parallel": true,
"self": 29.65865849498823,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.533757022222744,
"count": 464794,
"is_parallel": true,
"self": 54.533757022222744
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 492.97900852451494,
"count": 232398,
"self": 6.1522792546884375,
"children": {
"process_trajectory": {
"total": 160.1696330058321,
"count": 232398,
"self": 158.84911255683073,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3205204490013784,
"count": 10,
"self": 1.3205204490013784
}
}
},
"_update_policy": {
"total": 326.6570962639944,
"count": 97,
"self": 259.8714455479767,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.7856507160177,
"count": 2910,
"self": 66.7856507160177
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2489999789977446e-06,
"count": 1,
"self": 1.2489999789977446e-06
},
"TrainerController._save_models": {
"total": 0.18561544600015623,
"count": 1,
"self": 0.006051692000255571,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17956375399990065,
"count": 1,
"self": 0.17956375399990065
}
}
}
}
}
}
}