ppo-Pyramids / run_logs /timers.json
drakrig's picture
First Push
c6fab06 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5683950185775757,
"min": 0.5236718058586121,
"max": 1.4134854078292847,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 16888.15234375,
"min": 15517.443359375,
"max": 42879.4921875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989899.0,
"min": 29952.0,
"max": 989899.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989899.0,
"min": 29952.0,
"max": 989899.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.07027161121368408,
"min": -0.10980428755283356,
"max": 0.07986406981945038,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 17.286815643310547,
"min": -26.462833404541016,
"max": 19.886154174804688,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.05760909244418144,
"min": 0.035029709339141846,
"max": 0.4238227605819702,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 14.171836853027344,
"min": 8.477190017700195,
"max": 101.71746063232422,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07016126873453946,
"min": 0.06379992625450558,
"max": 0.07383666773615725,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9822577622835524,
"min": 0.4999359687295175,
"max": 1.0291900774001772,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.006318104471488153,
"min": 0.0001443857884778902,
"max": 0.011620754715258,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.08845346260083414,
"min": 0.0015882436732567921,
"max": 0.10053300234384925,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 4.909326116814288e-06,
"min": 4.909326116814288e-06,
"max": 0.0001967670873307428,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 6.873056563540004e-05,
"min": 6.873056563540004e-05,
"max": 0.001860722269639,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1024546142857143,
"min": 0.1024546142857143,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4343646,
"min": 1.3691136000000002,
"max": 2.316816,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025521596714285727,
"min": 0.00025521596714285727,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0035730235400000016,
"min": 0.0035730235400000016,
"max": 0.0930630639,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.03848887234926224,
"min": 0.03848887234926224,
"max": 0.6391104459762573,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.5388442277908325,
"min": 0.5388442277908325,
"max": 4.473773002624512,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 814.4,
"min": 766.2820512820513,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28504.0,
"min": 15984.0,
"max": 32111.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.15672566954578673,
"min": -1.0000000521540642,
"max": 0.310343542160132,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 5.485398434102535,
"min": -32.000001668930054,
"max": 12.103398144245148,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.15672566954578673,
"min": -1.0000000521540642,
"max": 0.310343542160132,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 5.485398434102535,
"min": -32.000001668930054,
"max": 12.103398144245148,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.3217500672808715,
"min": 0.31017828419900095,
"max": 13.27665263786912,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 11.261252354830503,
"min": 11.261252354830503,
"max": 212.42644220590591,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1709376887",
"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/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1709378842"
},
"total": 1954.94241857,
"count": 1,
"self": 0.48625732399978006,
"children": {
"run_training.setup": {
"total": 0.04728379100015445,
"count": 1,
"self": 0.04728379100015445
},
"TrainerController.start_learning": {
"total": 1954.408877455,
"count": 1,
"self": 1.2521684639968953,
"children": {
"TrainerController._reset_env": {
"total": 3.087941075999879,
"count": 1,
"self": 3.087941075999879
},
"TrainerController.advance": {
"total": 1949.9809655280033,
"count": 63001,
"self": 1.3072588418308442,
"children": {
"env_step": {
"total": 1342.7503709570665,
"count": 63001,
"self": 1217.9953956679637,
"children": {
"SubprocessEnvManager._take_step": {
"total": 123.99543236808222,
"count": 63001,
"self": 4.406311193030888,
"children": {
"TorchPolicy.evaluate": {
"total": 119.58912117505133,
"count": 62548,
"self": 119.58912117505133
}
}
},
"workers": {
"total": 0.7595429210205111,
"count": 63001,
"self": 0.0,
"children": {
"worker_root": {
"total": 1949.8310138320312,
"count": 63001,
"is_parallel": true,
"self": 839.8693725230323,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0024710519992368063,
"count": 1,
"is_parallel": true,
"self": 0.0006806859983043978,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017903660009324085,
"count": 8,
"is_parallel": true,
"self": 0.0017903660009324085
}
}
},
"UnityEnvironment.step": {
"total": 0.04906750100053614,
"count": 1,
"is_parallel": true,
"self": 0.0005751290009357035,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004706899999291636,
"count": 1,
"is_parallel": true,
"self": 0.0004706899999291636
},
"communicator.exchange": {
"total": 0.04640767499950016,
"count": 1,
"is_parallel": true,
"self": 0.04640767499950016
},
"steps_from_proto": {
"total": 0.0016140070001711138,
"count": 1,
"is_parallel": true,
"self": 0.0003368739980942337,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00127713300207688,
"count": 8,
"is_parallel": true,
"self": 0.00127713300207688
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1109.9616413089989,
"count": 63000,
"is_parallel": true,
"self": 33.62503092260431,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.184996542240697,
"count": 63000,
"is_parallel": true,
"self": 23.184996542240697
},
"communicator.exchange": {
"total": 958.7983724060596,
"count": 63000,
"is_parallel": true,
"self": 958.7983724060596
},
"steps_from_proto": {
"total": 94.3532414380943,
"count": 63000,
"is_parallel": true,
"self": 18.395272954394386,
"children": {
"_process_rank_one_or_two_observation": {
"total": 75.95796848369991,
"count": 504000,
"is_parallel": true,
"self": 75.95796848369991
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 605.9233357291059,
"count": 63001,
"self": 2.3106603891283157,
"children": {
"process_trajectory": {
"total": 118.51538528198307,
"count": 63001,
"self": 118.32995821098302,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18542707100004918,
"count": 2,
"self": 0.18542707100004918
}
}
},
"_update_policy": {
"total": 485.09729005799454,
"count": 424,
"self": 285.30011627393924,
"children": {
"TorchPPOOptimizer.update": {
"total": 199.7971737840553,
"count": 22890,
"self": 199.7971737840553
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.300003173644654e-07,
"count": 1,
"self": 8.300003173644654e-07
},
"TrainerController._save_models": {
"total": 0.08780155699969328,
"count": 1,
"self": 0.001371786999698088,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08642976999999519,
"count": 1,
"self": 0.08642976999999519
}
}
}
}
}
}
}