PPO-PyramidsRND / run_logs /timers.json
oukhan's picture
First Push
ca976e3 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.37224334478378296,
"min": 0.3396977186203003,
"max": 1.4676240682601929,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 11149.4326171875,
"min": 10185.49609375,
"max": 44521.84375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989952.0,
"min": 29952.0,
"max": 989952.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989952.0,
"min": 29952.0,
"max": 989952.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.42376869916915894,
"min": -0.11046431213617325,
"max": 0.44332370162010193,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 113.57001495361328,
"min": -26.51143455505371,
"max": 119.40064239501953,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.021327713504433632,
"min": 0.010403959080576897,
"max": 0.3670308589935303,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 5.715826988220215,
"min": 2.5489699840545654,
"max": 86.98631286621094,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06958609954987574,
"min": 0.06361613437580656,
"max": 0.07180004949712657,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9742053936982604,
"min": 0.48820993700934484,
"max": 1.0770007424568986,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01288961323284422,
"min": 0.00017544921408062876,
"max": 0.013623122584249357,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.18045458525981908,
"min": 0.002280839783048174,
"max": 0.19694611737941162,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.662183160257147e-06,
"min": 7.662183160257147e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010727056424360007,
"min": 0.00010727056424360007,
"max": 0.0036331093889635994,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10255402857142858,
"min": 0.10255402857142858,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4357564,
"min": 1.3886848,
"max": 2.6110364,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002651474542857145,
"min": 0.0002651474542857145,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0037120643600000026,
"min": 0.0037120643600000026,
"max": 0.12112253636,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01465486828237772,
"min": 0.01465486828237772,
"max": 0.42845073342323303,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.20516815781593323,
"min": 0.20516815781593323,
"max": 2.999155044555664,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 456.5,
"min": 397.95652173913044,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31042.0,
"min": 15984.0,
"max": 33010.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.3322089338925347,
"min": -1.0000000521540642,
"max": 1.5440637458493744,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 89.25799857079983,
"min": -31.992801651358604,
"max": 106.54039846360683,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.3322089338925347,
"min": -1.0000000521540642,
"max": 1.5440637458493744,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 89.25799857079983,
"min": -31.992801651358604,
"max": 106.54039846360683,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.06892447468282571,
"min": 0.061678926256929015,
"max": 8.535530452616513,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.617939803749323,
"min": 4.255845911728102,
"max": 136.5684872418642,
"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": "1769578478",
"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/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1769581708"
},
"total": 3229.708704148,
"count": 1,
"self": 1.1432437759995082,
"children": {
"run_training.setup": {
"total": 0.0398349940001026,
"count": 1,
"self": 0.0398349940001026
},
"TrainerController.start_learning": {
"total": 3228.5256253780003,
"count": 1,
"self": 2.2459369640796467,
"children": {
"TrainerController._reset_env": {
"total": 4.213645554999857,
"count": 1,
"self": 4.213645554999857
},
"TrainerController.advance": {
"total": 3221.9452761069206,
"count": 63547,
"self": 2.3621367257733255,
"children": {
"env_step": {
"total": 2156.83783200009,
"count": 63547,
"self": 1995.8382878810226,
"children": {
"SubprocessEnvManager._take_step": {
"total": 159.60703691503386,
"count": 63547,
"self": 6.693517651985076,
"children": {
"TorchPolicy.evaluate": {
"total": 152.91351926304878,
"count": 62549,
"self": 152.91351926304878
}
}
},
"workers": {
"total": 1.392507204033791,
"count": 63547,
"self": 0.0,
"children": {
"worker_root": {
"total": 3220.529878414967,
"count": 63547,
"is_parallel": true,
"self": 1403.6991322798508,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0025681669999357837,
"count": 1,
"is_parallel": true,
"self": 0.0007530019997830095,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018151650001527742,
"count": 8,
"is_parallel": true,
"self": 0.0018151650001527742
}
}
},
"UnityEnvironment.step": {
"total": 0.07068140299998049,
"count": 1,
"is_parallel": true,
"self": 0.0006525059998239158,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005399140000008629,
"count": 1,
"is_parallel": true,
"self": 0.0005399140000008629
},
"communicator.exchange": {
"total": 0.06742933099985748,
"count": 1,
"is_parallel": true,
"self": 0.06742933099985748
},
"steps_from_proto": {
"total": 0.002059652000298229,
"count": 1,
"is_parallel": true,
"self": 0.000405968999984907,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016536830003133218,
"count": 8,
"is_parallel": true,
"self": 0.0016536830003133218
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1816.830746135116,
"count": 63546,
"is_parallel": true,
"self": 44.735808680409264,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 31.01364134382402,
"count": 63546,
"is_parallel": true,
"self": 31.01364134382402
},
"communicator.exchange": {
"total": 1598.7290253270444,
"count": 63546,
"is_parallel": true,
"self": 1598.7290253270444
},
"steps_from_proto": {
"total": 142.35227078383832,
"count": 63546,
"is_parallel": true,
"self": 28.56369747168992,
"children": {
"_process_rank_one_or_two_observation": {
"total": 113.7885733121484,
"count": 508368,
"is_parallel": true,
"self": 113.7885733121484
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1062.745307381057,
"count": 63547,
"self": 4.2705297851293835,
"children": {
"process_trajectory": {
"total": 156.35797263492123,
"count": 63547,
"self": 156.00209761992255,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3558750149986736,
"count": 2,
"self": 0.3558750149986736
}
}
},
"_update_policy": {
"total": 902.1168049610064,
"count": 453,
"self": 356.99205118903865,
"children": {
"TorchPPOOptimizer.update": {
"total": 545.1247537719678,
"count": 22797,
"self": 545.1247537719678
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.635999979043845e-06,
"count": 1,
"self": 1.635999979043845e-06
},
"TrainerController._save_models": {
"total": 0.12076511600025697,
"count": 1,
"self": 0.0019557510004233336,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11880936499983363,
"count": 1,
"self": 0.11880936499983363
}
}
}
}
}
}
}