ppo-Huggy / run_logs /timers.json
jacksonhack's picture
Huggy
ef6cea6 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4100924730300903,
"min": 1.4100924730300903,
"max": 1.4310270547866821,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69930.71875,
"min": 68448.9921875,
"max": 76529.328125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 122.3925,
"min": 118.51201923076923,
"max": 406.0243902439024,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 48957.0,
"min": 48957.0,
"max": 50247.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999990.0,
"min": 49407.0,
"max": 1999990.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999990.0,
"min": 49407.0,
"max": 1999990.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.2869701385498047,
"min": 0.054526280611753464,
"max": 2.289613962173462,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 914.7880859375,
"min": 6.6522064208984375,
"max": 936.4520874023438,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.572374954670668,
"min": 1.865826356728546,
"max": 3.7202447517735426,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1428.949981868267,
"min": 227.6308155208826,
"max": 1487.8043401241302,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.572374954670668,
"min": 1.865826356728546,
"max": 3.7202447517735426,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1428.949981868267,
"min": 227.6308155208826,
"max": 1487.8043401241302,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01853179479318593,
"min": 0.014552703478451199,
"max": 0.021207068672326083,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03706358958637186,
"min": 0.029105406956902398,
"max": 0.05701256228882509,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.044729003993173436,
"min": 0.022120755600432557,
"max": 0.05611583213839266,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.08945800798634687,
"min": 0.04424151120086511,
"max": 0.168347496415178,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.519298493599991e-06,
"min": 4.519298493599991e-06,
"max": 0.00029530770156409997,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.038596987199982e-06,
"min": 9.038596987199982e-06,
"max": 0.0008442360185879999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10150639999999998,
"min": 0.10150639999999998,
"max": 0.19843589999999997,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20301279999999997,
"min": 0.20301279999999997,
"max": 0.581412,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.516935999999986e-05,
"min": 8.516935999999986e-05,
"max": 0.00492195141,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00017033871999999972,
"min": 0.00017033871999999972,
"max": 0.014072458799999998,
"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": "1730163047",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/home/jackson/miniconda3/envs/python_3.10.12/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1730165963"
},
"total": 2915.7002556200023,
"count": 1,
"self": 1.3351774230031879,
"children": {
"run_training.setup": {
"total": 0.02041659699898446,
"count": 1,
"self": 0.02041659699898446
},
"TrainerController.start_learning": {
"total": 2914.3446616,
"count": 1,
"self": 4.823203408355766,
"children": {
"TrainerController._reset_env": {
"total": 2.583311442002014,
"count": 1,
"self": 2.583311442002014
},
"TrainerController.advance": {
"total": 2906.8620340896377,
"count": 229554,
"self": 4.166171206372383,
"children": {
"env_step": {
"total": 2170.103771995942,
"count": 229554,
"self": 1858.3505464718473,
"children": {
"SubprocessEnvManager._take_step": {
"total": 308.34877743814286,
"count": 229554,
"self": 21.248596632198314,
"children": {
"TorchPolicy.evaluate": {
"total": 287.10018080594455,
"count": 222943,
"self": 287.10018080594455
}
}
},
"workers": {
"total": 3.4044480859520263,
"count": 229554,
"self": 0.0,
"children": {
"worker_root": {
"total": 2902.941041298858,
"count": 229554,
"is_parallel": true,
"self": 1326.9436627891118,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0006807270037825219,
"count": 1,
"is_parallel": true,
"self": 0.00017309500981355086,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005076319939689711,
"count": 2,
"is_parallel": true,
"self": 0.0005076319939689711
}
}
},
"UnityEnvironment.step": {
"total": 0.018186165994848125,
"count": 1,
"is_parallel": true,
"self": 0.0003679699875647202,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019954399613197893,
"count": 1,
"is_parallel": true,
"self": 0.00019954399613197893
},
"communicator.exchange": {
"total": 0.017302349006058648,
"count": 1,
"is_parallel": true,
"self": 0.017302349006058648
},
"steps_from_proto": {
"total": 0.0003163030050927773,
"count": 1,
"is_parallel": true,
"self": 8.301599882543087e-05,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00023328700626734644,
"count": 2,
"is_parallel": true,
"self": 0.00023328700626734644
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1575.9973785097463,
"count": 229553,
"is_parallel": true,
"self": 29.123578510640073,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 66.63107418676373,
"count": 229553,
"is_parallel": true,
"self": 66.63107418676373
},
"communicator.exchange": {
"total": 1422.134730379068,
"count": 229553,
"is_parallel": true,
"self": 1422.134730379068
},
"steps_from_proto": {
"total": 58.10799543327448,
"count": 229553,
"is_parallel": true,
"self": 16.804826797480928,
"children": {
"_process_rank_one_or_two_observation": {
"total": 41.303168635793554,
"count": 459106,
"is_parallel": true,
"self": 41.303168635793554
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 732.5920908873231,
"count": 229554,
"self": 8.193471307589789,
"children": {
"process_trajectory": {
"total": 123.68724299575842,
"count": 229554,
"self": 122.85609987775388,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8311431180045474,
"count": 10,
"self": 0.8311431180045474
}
}
},
"_update_policy": {
"total": 600.7113765839749,
"count": 96,
"self": 178.79236740776105,
"children": {
"TorchPPOOptimizer.update": {
"total": 421.9190091762139,
"count": 2880,
"self": 421.9190091762139
}
}
}
}
}
}
},
"trainer_threads": {
"total": 6.010013748891652e-07,
"count": 1,
"self": 6.010013748891652e-07
},
"TrainerController._save_models": {
"total": 0.07611205900320783,
"count": 1,
"self": 0.0029703600011998788,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07314169900200795,
"count": 1,
"self": 0.07314169900200795
}
}
}
}
}
}
}