ppo-PyramidsRND / run_logs /timers.json
bobobert4's picture
First commit
2529f04
raw
history blame
18.7 kB
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.28890180587768555,
"min": 0.2679888904094696,
"max": 1.3829582929611206,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 8620.830078125,
"min": 7966.77392578125,
"max": 41953.421875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989874.0,
"min": 29952.0,
"max": 989874.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989874.0,
"min": 29952.0,
"max": 989874.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.20401406288146973,
"min": -0.06647870689630508,
"max": 0.2703288495540619,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 52.02358627319336,
"min": -16.087846755981445,
"max": 70.3196792602539,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.5786445736885071,
"min": 0.5597960352897644,
"max": 8.965831756591797,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 147.5543670654297,
"min": 145.54696655273438,
"max": 2160.765380859375,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.04788420050721874,
"min": 0.0441769959924314,
"max": 0.053672307848169044,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.38307360405774993,
"min": 0.29910242225883077,
"max": 0.4218484266990951,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.008147297955414008,
"min": 0.0026935507330187922,
"max": 1.9088322994854263,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.06517838364331206,
"min": 0.018854855131131547,
"max": 11.452993796912558,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.723634925487498e-06,
"min": 7.723634925487498e-06,
"max": 0.0002954496015168,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 6.178907940389999e-05,
"min": 6.178907940389999e-05,
"max": 0.0020060661313113,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1025745125,
"min": 0.1025745125,
"max": 0.1984832,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 0.8205961,
"min": 0.7393368000000001,
"max": 1.4203899,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026719379875,
"min": 0.00026719379875,
"max": 0.00984847168,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.00213755039,
"min": 0.00213755039,
"max": 0.06687200113000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.03691082447767258,
"min": 0.03582962974905968,
"max": 0.8141033053398132,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.2952865958213806,
"min": 0.25080740451812744,
"max": 4.88461971282959,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 560.5769230769231,
"min": 481.1639344262295,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29150.0,
"min": 15984.0,
"max": 32372.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.0931422721881132,
"min": -1.0000000521540642,
"max": 1.3876557149848,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 56.84339815378189,
"min": -31.99920167028904,
"max": 84.6469986140728,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.8745139822936975,
"min": -0.7999998107552528,
"max": 1.1101246915879797,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 45.47472707927227,
"min": -25.599353954195976,
"max": 67.71760618686676,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 3.1499521787314175,
"min": 2.746701407368432,
"max": 193.41542422771454,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 163.7975132940337,
"min": 163.7975132940337,
"max": 3094.6467876434326,
"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": "1689923152",
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsRND_0 --no-graphics --force",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1689925146"
},
"total": 1993.668715329999,
"count": 1,
"self": 0.4754512399995292,
"children": {
"run_training.setup": {
"total": 0.030952627999795368,
"count": 1,
"self": 0.030952627999795368
},
"TrainerController.start_learning": {
"total": 1993.1623114619997,
"count": 1,
"self": 1.2599244319335412,
"children": {
"TrainerController._reset_env": {
"total": 4.087754534000851,
"count": 1,
"self": 4.087754534000851
},
"TrainerController.advance": {
"total": 1987.720824812066,
"count": 63527,
"self": 1.2695256993938528,
"children": {
"env_step": {
"total": 1460.9425883774766,
"count": 63527,
"self": 1354.918614247952,
"children": {
"SubprocessEnvManager._take_step": {
"total": 105.25268689018594,
"count": 63527,
"self": 4.632025678169157,
"children": {
"TorchPolicy.evaluate": {
"total": 100.62066121201678,
"count": 62573,
"self": 100.62066121201678
}
}
},
"workers": {
"total": 0.7712872393385624,
"count": 63527,
"self": 0.0,
"children": {
"worker_root": {
"total": 1988.4170024500036,
"count": 63527,
"is_parallel": true,
"self": 742.7113994140545,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018512749993533362,
"count": 1,
"is_parallel": true,
"self": 0.0005571689962380333,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012941060031153029,
"count": 8,
"is_parallel": true,
"self": 0.0012941060031153029
}
}
},
"UnityEnvironment.step": {
"total": 0.047071117000086815,
"count": 1,
"is_parallel": true,
"self": 0.0006164869992062449,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004810410009667976,
"count": 1,
"is_parallel": true,
"self": 0.0004810410009667976
},
"communicator.exchange": {
"total": 0.044154719998914516,
"count": 1,
"is_parallel": true,
"self": 0.044154719998914516
},
"steps_from_proto": {
"total": 0.001818869000999257,
"count": 1,
"is_parallel": true,
"self": 0.0003691240035550436,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014497449974442134,
"count": 8,
"is_parallel": true,
"self": 0.0014497449974442134
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1245.705603035949,
"count": 63526,
"is_parallel": true,
"self": 32.962512950869495,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.696410784083128,
"count": 63526,
"is_parallel": true,
"self": 22.696410784083128
},
"communicator.exchange": {
"total": 1091.991832782116,
"count": 63526,
"is_parallel": true,
"self": 1091.991832782116
},
"steps_from_proto": {
"total": 98.05484651888037,
"count": 63526,
"is_parallel": true,
"self": 19.377185984210882,
"children": {
"_process_rank_one_or_two_observation": {
"total": 78.67766053466949,
"count": 508208,
"is_parallel": true,
"self": 78.67766053466949
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 525.5087107351956,
"count": 63527,
"self": 2.2891563113116717,
"children": {
"process_trajectory": {
"total": 107.08924092787129,
"count": 63527,
"self": 106.88473367387269,
"children": {
"RLTrainer._checkpoint": {
"total": 0.20450725399859948,
"count": 2,
"self": 0.20450725399859948
}
}
},
"_update_policy": {
"total": 416.1303134960126,
"count": 241,
"self": 315.5505503180066,
"children": {
"TorchPPOOptimizer.update": {
"total": 100.57976317800603,
"count": 11265,
"self": 100.57976317800603
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.889990906231105e-07,
"count": 1,
"self": 9.889990906231105e-07
},
"TrainerController._save_models": {
"total": 0.09380669500023942,
"count": 1,
"self": 0.0013669799991475884,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09243971500109183,
"count": 1,
"self": 0.09243971500109183
}
}
}
}
}
}
}