ppo-Pyramids / run_logs /timers.json
execbat's picture
123
a3bb8f6 verified
raw
history blame
18.9 kB
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.16614551842212677,
"min": 0.15744175016880035,
"max": 0.4004281461238861,
"count": 67
},
"Pyramids.Policy.Entropy.sum": {
"value": 4973.732421875,
"min": 4705.619140625,
"max": 11863.4970703125,
"count": 67
},
"Pyramids.Step.mean": {
"value": 2999939.0,
"min": 1019985.0,
"max": 2999939.0,
"count": 67
},
"Pyramids.Step.sum": {
"value": 2999939.0,
"min": 1019985.0,
"max": 2999939.0,
"count": 67
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.7775925397872925,
"min": 0.38037940859794617,
"max": 0.8467114567756653,
"count": 67
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 234.83294677734375,
"min": 68.46829223632812,
"max": 255.720947265625,
"count": 67
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.007298759184777737,
"min": -0.027858613058924675,
"max": 0.025125911459326744,
"count": 67
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 2.2042253017425537,
"min": -8.078997611999512,
"max": 6.985003471374512,
"count": 67
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 227.94202898550725,
"min": 214.1203007518797,
"max": 400.73333333333335,
"count": 67
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31456.0,
"min": 17453.0,
"max": 32858.0,
"count": 67
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7575637530805408,
"min": 1.4404605014347716,
"max": 1.7773153729163684,
"count": 67
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 242.54379792511463,
"min": 75.01299963891506,
"max": 242.54379792511463,
"count": 67
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7575637530805408,
"min": 1.4404605014347716,
"max": 1.7773153729163684,
"count": 67
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 242.54379792511463,
"min": 75.01299963891506,
"max": 242.54379792511463,
"count": 67
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.01710802239667037,
"min": 0.01619614733618046,
"max": 0.04663682050350441,
"count": 67
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.360907090740511,
"min": 2.068932451773435,
"max": 3.5917186766237137,
"count": 67
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06744252901504902,
"min": 0.06230993422515759,
"max": 0.07262886023446401,
"count": 67
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9441954062106863,
"min": 0.5607894080264183,
"max": 1.08943290351696,
"count": 67
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.014559747672700768,
"min": 0.01243803503201066,
"max": 0.017963412353613727,
"count": 67
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.20383646741781075,
"min": 0.13917270860595937,
"max": 0.25148777295059216,
"count": 67
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.5530066252214284e-06,
"min": 1.5530066252214284e-06,
"max": 0.0001989427559079815,
"count": 67
},
"Pyramids.Policy.LearningRate.sum": {
"value": 2.1742092753099997e-05,
"min": 2.1742092753099997e-05,
"max": 0.0029021046326319667,
"count": 67
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10051763571428572,
"min": 0.10051763571428572,
"max": 0.16631424074074078,
"count": 67
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4072469,
"min": 1.4072469,
"max": 2.4673680333333334,
"count": 67
},
"Pyramids.Policy.Beta.mean": {
"value": 6.171180785714287e-05,
"min": 6.171180785714287e-05,
"max": 0.0066347926500000005,
"count": 67
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0008639653100000002,
"min": 0.0008639653100000002,
"max": 0.09679006653000001,
"count": 67
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.0071940673515200615,
"min": 0.006953801028430462,
"max": 0.011702639050781727,
"count": 67
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.10071694105863571,
"min": 0.09735321253538132,
"max": 0.16821780800819397,
"count": 67
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 67
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 67
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1720177071",
"python_version": "3.10.5 | packaged by conda-forge | (main, Jun 14 2022, 07:06:46) [GCC 10.3.0]",
"command_line_arguments": "/home/evgenii/anaconda3/envs/hf_unit_5/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1720179159"
},
"total": 2087.9573382630006,
"count": 1,
"self": 0.2699226140011888,
"children": {
"run_training.setup": {
"total": 0.014744360998520278,
"count": 1,
"self": 0.014744360998520278
},
"TrainerController.start_learning": {
"total": 2087.672671288001,
"count": 1,
"self": 1.9585120793944952,
"children": {
"TrainerController._reset_env": {
"total": 1.3706379960003687,
"count": 1,
"self": 1.3706379960003687
},
"TrainerController.advance": {
"total": 2084.2557300056033,
"count": 130809,
"self": 1.8958319506164116,
"children": {
"env_step": {
"total": 1308.126472861777,
"count": 130809,
"self": 1134.1034976238734,
"children": {
"SubprocessEnvManager._take_step": {
"total": 172.85623305369518,
"count": 130809,
"self": 5.380244661882898,
"children": {
"TorchPolicy.evaluate": {
"total": 167.47598839181228,
"count": 125062,
"self": 167.47598839181228
}
}
},
"workers": {
"total": 1.1667421842084877,
"count": 130809,
"self": 0.0,
"children": {
"worker_root": {
"total": 2085.3082336531043,
"count": 130809,
"is_parallel": true,
"self": 1079.35512368122,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009861980015557492,
"count": 1,
"is_parallel": true,
"self": 0.0002878070008591749,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006983910006965743,
"count": 8,
"is_parallel": true,
"self": 0.0006983910006965743
}
}
},
"UnityEnvironment.step": {
"total": 0.02389382199908141,
"count": 1,
"is_parallel": true,
"self": 0.00020229999790899456,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00017607799964025617,
"count": 1,
"is_parallel": true,
"self": 0.00017607799964025617
},
"communicator.exchange": {
"total": 0.02289140600078099,
"count": 1,
"is_parallel": true,
"self": 0.02289140600078099
},
"steps_from_proto": {
"total": 0.0006240380007511703,
"count": 1,
"is_parallel": true,
"self": 0.00015289700058929157,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00047114100016187876,
"count": 8,
"is_parallel": true,
"self": 0.00047114100016187876
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1005.9531099718843,
"count": 130808,
"is_parallel": true,
"self": 26.559794868169774,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 18.87666513197837,
"count": 130808,
"is_parallel": true,
"self": 18.87666513197837
},
"communicator.exchange": {
"total": 880.9345199697709,
"count": 130808,
"is_parallel": true,
"self": 880.9345199697709
},
"steps_from_proto": {
"total": 79.5821300019652,
"count": 130808,
"is_parallel": true,
"self": 18.462800923911345,
"children": {
"_process_rank_one_or_two_observation": {
"total": 61.11932907805385,
"count": 1046464,
"is_parallel": true,
"self": 61.11932907805385
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 774.2334251932098,
"count": 130809,
"self": 3.282825667904035,
"children": {
"process_trajectory": {
"total": 160.4229674473081,
"count": 130809,
"self": 160.06058368130834,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3623837659997662,
"count": 4,
"self": 0.3623837659997662
}
}
},
"_update_policy": {
"total": 610.5276320779976,
"count": 946,
"self": 355.50618573900465,
"children": {
"TorchPPOOptimizer.update": {
"total": 255.02144633899297,
"count": 45519,
"self": 255.02144633899297
}
}
}
}
}
}
},
"trainer_threads": {
"total": 6.630016287090257e-07,
"count": 1,
"self": 6.630016287090257e-07
},
"TrainerController._save_models": {
"total": 0.08779054400110908,
"count": 1,
"self": 0.0011630470016825711,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08662749699942651,
"count": 1,
"self": 0.08662749699942651
}
}
}
}
}
}
}