ppo-Huggy / run_logs /timers.json
sid22669's picture
Huggy
8b144b0 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.411881685256958,
"min": 1.411881685256958,
"max": 1.4283241033554077,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70451.484375,
"min": 69271.3359375,
"max": 75416.8359375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 82.44776119402985,
"min": 78.23296354992075,
"max": 394.2204724409449,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49716.0,
"min": 48946.0,
"max": 50091.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999625.0,
"min": 49456.0,
"max": 1999625.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999625.0,
"min": 49456.0,
"max": 1999625.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4681155681610107,
"min": 0.07327212393283844,
"max": 2.5079591274261475,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1488.273681640625,
"min": 9.232287406921387,
"max": 1563.17138671875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9190705799147065,
"min": 1.793542326442779,
"max": 4.076686027406276,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2363.199559688568,
"min": 225.98633313179016,
"max": 2482.701790690422,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9190705799147065,
"min": 1.793542326442779,
"max": 4.076686027406276,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2363.199559688568,
"min": 225.98633313179016,
"max": 2482.701790690422,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016677808188574596,
"min": 0.013768567787095284,
"max": 0.019339043200278006,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05003342456572379,
"min": 0.027537135574190567,
"max": 0.058017129600834015,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05848237151900928,
"min": 0.021525195272018512,
"max": 0.06470965277403593,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17544711455702783,
"min": 0.043050390544037025,
"max": 0.18414022823174794,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5454988181999984e-06,
"min": 3.5454988181999984e-06,
"max": 0.00029526262657912487,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0636496454599996e-05,
"min": 1.0636496454599996e-05,
"max": 0.0008439348186883998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10118180000000003,
"min": 0.10118180000000003,
"max": 0.198420875,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3035454000000001,
"min": 0.207516,
"max": 0.5813115999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.897181999999999e-05,
"min": 6.897181999999999e-05,
"max": 0.004921201662499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020691545999999996,
"min": 0.00020691545999999996,
"max": 0.014067448840000002,
"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": "1748772347",
"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",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1748774721"
},
"total": 2374.45636439,
"count": 1,
"self": 0.4412948139997752,
"children": {
"run_training.setup": {
"total": 0.02287382700001217,
"count": 1,
"self": 0.02287382700001217
},
"TrainerController.start_learning": {
"total": 2373.992195749,
"count": 1,
"self": 4.107492147966241,
"children": {
"TrainerController._reset_env": {
"total": 3.402705021000088,
"count": 1,
"self": 3.402705021000088
},
"TrainerController.advance": {
"total": 2366.3756076090335,
"count": 232646,
"self": 4.392050452036983,
"children": {
"env_step": {
"total": 1874.0025822799148,
"count": 232646,
"self": 1470.6970640008808,
"children": {
"SubprocessEnvManager._take_step": {
"total": 400.75614942505604,
"count": 232646,
"self": 15.480932274038992,
"children": {
"TorchPolicy.evaluate": {
"total": 385.27521715101705,
"count": 222889,
"self": 385.27521715101705
}
}
},
"workers": {
"total": 2.549368853977853,
"count": 232646,
"self": 0.0,
"children": {
"worker_root": {
"total": 2367.0114402620375,
"count": 232646,
"is_parallel": true,
"self": 1168.3240846770332,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008158140000205094,
"count": 1,
"is_parallel": true,
"self": 0.0002363190000096438,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005794950000108656,
"count": 2,
"is_parallel": true,
"self": 0.0005794950000108656
}
}
},
"UnityEnvironment.step": {
"total": 0.028869408999980806,
"count": 1,
"is_parallel": true,
"self": 0.00030996899999991,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022084199997607357,
"count": 1,
"is_parallel": true,
"self": 0.00022084199997607357
},
"communicator.exchange": {
"total": 0.02766308200000367,
"count": 1,
"is_parallel": true,
"self": 0.02766308200000367
},
"steps_from_proto": {
"total": 0.0006755160000011529,
"count": 1,
"is_parallel": true,
"self": 0.00017455800002608157,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005009579999750713,
"count": 2,
"is_parallel": true,
"self": 0.0005009579999750713
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1198.6873555850043,
"count": 232645,
"is_parallel": true,
"self": 36.63856661097452,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.56294990806248,
"count": 232645,
"is_parallel": true,
"self": 78.56294990806248
},
"communicator.exchange": {
"total": 998.895980553007,
"count": 232645,
"is_parallel": true,
"self": 998.895980553007
},
"steps_from_proto": {
"total": 84.58985851296018,
"count": 232645,
"is_parallel": true,
"self": 29.892479640999227,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.69737887196095,
"count": 465290,
"is_parallel": true,
"self": 54.69737887196095
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 487.9809748770816,
"count": 232646,
"self": 6.449195647026386,
"children": {
"process_trajectory": {
"total": 158.52599725105426,
"count": 232646,
"self": 157.35290298405505,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1730942669992146,
"count": 10,
"self": 1.1730942669992146
}
}
},
"_update_policy": {
"total": 323.005781979001,
"count": 97,
"self": 256.70693817500444,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.29884380399653,
"count": 2910,
"self": 66.29884380399653
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.090003914025147e-07,
"count": 1,
"self": 9.090003914025147e-07
},
"TrainerController._save_models": {
"total": 0.10639006199971845,
"count": 1,
"self": 0.0016364899993277504,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1047535720003907,
"count": 1,
"self": 0.1047535720003907
}
}
}
}
}
}
}