ppo-Huggy / run_logs /timers.json
titantomorrow's picture
Huggy
d7fc3e3 verified
raw
history blame contribute delete
No virus
17.5 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4009710550308228,
"min": 1.4009438753128052,
"max": 1.4242117404937744,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 67767.7734375,
"min": 67767.7734375,
"max": 77274.3515625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 118.04047619047618,
"min": 98.23611111111111,
"max": 391.5703125,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49577.0,
"min": 48844.0,
"max": 50121.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999985.0,
"min": 49911.0,
"max": 1999985.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999985.0,
"min": 49911.0,
"max": 1999985.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.2244179248809814,
"min": 0.008883005939424038,
"max": 2.386794328689575,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 934.2555541992188,
"min": 1.1281417608261108,
"max": 1170.8104248046875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.2593543538025447,
"min": 1.957268141386077,
"max": 3.844730469956994,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1368.9288285970688,
"min": 248.5730539560318,
"max": 1889.750771164894,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.2593543538025447,
"min": 1.957268141386077,
"max": 3.844730469956994,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1368.9288285970688,
"min": 248.5730539560318,
"max": 1889.750771164894,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014453169944802842,
"min": 0.013801892399593877,
"max": 0.019059200961297998,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.028906339889605684,
"min": 0.028537193707112843,
"max": 0.05613028039903535,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04366604269792636,
"min": 0.023648163707305988,
"max": 0.054407611737648645,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.08733208539585272,
"min": 0.047296327414611976,
"max": 0.1587271377444267,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.308773563775006e-06,
"min": 4.308773563775006e-06,
"max": 0.0002953715265428251,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.617547127550013e-06,
"min": 8.617547127550013e-06,
"max": 0.00084405376864875,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10143622500000002,
"min": 0.10143622500000002,
"max": 0.19845717500000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20287245000000004,
"min": 0.20287245000000004,
"max": 0.5813512500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.16676275000001e-05,
"min": 8.16676275000001e-05,
"max": 0.0049230130325,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001633352550000002,
"min": 0.0001633352550000002,
"max": 0.014069427374999999,
"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": "1715509120",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1715513911"
},
"total": 4790.677798674999,
"count": 1,
"self": 0.5653869349998786,
"children": {
"run_training.setup": {
"total": 0.07869143699986125,
"count": 1,
"self": 0.07869143699986125
},
"TrainerController.start_learning": {
"total": 4790.033720302999,
"count": 1,
"self": 8.528051647859684,
"children": {
"TrainerController._reset_env": {
"total": 3.7943542209998213,
"count": 1,
"self": 3.7943542209998213
},
"TrainerController.advance": {
"total": 4777.598589020139,
"count": 231328,
"self": 8.406523614021353,
"children": {
"env_step": {
"total": 3078.4830953169167,
"count": 231328,
"self": 2567.69328938621,
"children": {
"SubprocessEnvManager._take_step": {
"total": 505.1720197049726,
"count": 231328,
"self": 32.894992129951106,
"children": {
"TorchPolicy.evaluate": {
"total": 472.2770275750215,
"count": 223003,
"self": 472.2770275750215
}
}
},
"workers": {
"total": 5.617786225734108,
"count": 231328,
"self": 0.0,
"children": {
"worker_root": {
"total": 4775.412017488041,
"count": 231328,
"is_parallel": true,
"self": 2741.8748908908374,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011114629999156023,
"count": 1,
"is_parallel": true,
"self": 0.0002839050000602583,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000827557999855344,
"count": 2,
"is_parallel": true,
"self": 0.000827557999855344
}
}
},
"UnityEnvironment.step": {
"total": 0.04784601300002578,
"count": 1,
"is_parallel": true,
"self": 0.0005514960000709834,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00030967399993642175,
"count": 1,
"is_parallel": true,
"self": 0.00030967399993642175
},
"communicator.exchange": {
"total": 0.04598430900000494,
"count": 1,
"is_parallel": true,
"self": 0.04598430900000494
},
"steps_from_proto": {
"total": 0.001000534000013431,
"count": 1,
"is_parallel": true,
"self": 0.00027223599977332924,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007282980002401018,
"count": 2,
"is_parallel": true,
"self": 0.0007282980002401018
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 2033.5371265972033,
"count": 231327,
"is_parallel": true,
"self": 62.93582418837468,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 98.50522140098474,
"count": 231327,
"is_parallel": true,
"self": 98.50522140098474
},
"communicator.exchange": {
"total": 1732.953678127996,
"count": 231327,
"is_parallel": true,
"self": 1732.953678127996
},
"steps_from_proto": {
"total": 139.14240287984785,
"count": 231327,
"is_parallel": true,
"self": 44.76456219285592,
"children": {
"_process_rank_one_or_two_observation": {
"total": 94.37784068699193,
"count": 462654,
"is_parallel": true,
"self": 94.37784068699193
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1690.7089700892016,
"count": 231328,
"self": 12.965616602171849,
"children": {
"process_trajectory": {
"total": 259.59306097803005,
"count": 231328,
"self": 258.11468689903154,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4783740789985131,
"count": 10,
"self": 1.4783740789985131
}
}
},
"_update_policy": {
"total": 1418.1502925089997,
"count": 96,
"self": 355.40073547400993,
"children": {
"TorchPPOOptimizer.update": {
"total": 1062.7495570349897,
"count": 2880,
"self": 1062.7495570349897
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2590007827384397e-06,
"count": 1,
"self": 1.2590007827384397e-06
},
"TrainerController._save_models": {
"total": 0.1127241550002509,
"count": 1,
"self": 0.0028759639999407227,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10984819100031018,
"count": 1,
"self": 0.10984819100031018
}
}
}
}
}
}
}