Y-T-G's picture
First Push
7f09426
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.7879307866096497,
"min": 0.7798956036567688,
"max": 1.4863524436950684,
"count": 16
},
"Pyramids.Policy.Entropy.sum": {
"value": 23411.0,
"min": 23411.0,
"max": 45089.98828125,
"count": 16
},
"Pyramids.Step.mean": {
"value": 479977.0,
"min": 29939.0,
"max": 479977.0,
"count": 16
},
"Pyramids.Step.sum": {
"value": 479977.0,
"min": 29939.0,
"max": 479977.0,
"count": 16
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.30129289627075195,
"min": -0.11709693819284439,
"max": 0.30129289627075195,
"count": 16
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 77.1309814453125,
"min": -27.75197410583496,
"max": 77.1309814453125,
"count": 16
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.02765870839357376,
"min": 0.02012721635401249,
"max": 0.3780697286128998,
"count": 16
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 7.080629348754883,
"min": 5.051931381225586,
"max": 89.60252380371094,
"count": 16
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06748696474489312,
"min": 0.0664296471239074,
"max": 0.07312290836374974,
"count": 16
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0123044711733968,
"min": 0.6581061752737477,
"max": 1.0123044711733968,
"count": 16
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.011431089166462044,
"min": 0.0007473888176604587,
"max": 0.011511775219959487,
"count": 16
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.17146633749693066,
"min": 0.009716054629585963,
"max": 0.17146633749693066,
"count": 16
},
"Pyramids.Policy.LearningRate.mean": {
"value": 2.1010732996453333e-05,
"min": 2.1010732996453333e-05,
"max": 0.0002897527367490888,
"count": 16
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0003151609949468,
"min": 0.0003151609949468,
"max": 0.0033170515943161997,
"count": 16
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10700354666666666,
"min": 0.10700354666666666,
"max": 0.19658424444444444,
"count": 16
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.6050532,
"min": 1.5846114,
"max": 2.4056838000000003,
"count": 16
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0007096543119999999,
"min": 0.0007096543119999999,
"max": 0.009658766019999999,
"count": 16
},
"Pyramids.Policy.Beta.sum": {
"value": 0.01064481468,
"min": 0.01064481468,
"max": 0.11058781162,
"count": 16
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01675165630877018,
"min": 0.01675165630877018,
"max": 0.3614523708820343,
"count": 16
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.25127485394477844,
"min": 0.25127485394477844,
"max": 3.2530713081359863,
"count": 16
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 602.3921568627451,
"min": 555.48,
"max": 990.25,
"count": 16
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30722.0,
"min": 16610.0,
"max": 33407.0,
"count": 16
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.9661332979506138,
"min": -0.9286187971010804,
"max": 1.0827842885080505,
"count": 16
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 49.2727981954813,
"min": -30.240801632404327,
"max": 55.22199871391058,
"count": 16
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.9661332979506138,
"min": -0.9286187971010804,
"max": 1.0827842885080505,
"count": 16
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 49.2727981954813,
"min": -30.240801632404327,
"max": 55.22199871391058,
"count": 16
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.10569652314434815,
"min": 0.10540710396804463,
"max": 6.297938686959884,
"count": 16
},
"Pyramids.Policy.RndReward.sum": {
"value": 5.390522680361755,
"min": 5.375762302370276,
"max": 107.06495767831802,
"count": 16
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 16
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 16
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1679241732",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"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": "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": "1679242795"
},
"total": 1063.623661226,
"count": 1,
"self": 0.922740370999918,
"children": {
"run_training.setup": {
"total": 0.2208115099999759,
"count": 1,
"self": 0.2208115099999759
},
"TrainerController.start_learning": {
"total": 1062.480109345,
"count": 1,
"self": 0.7289624619922961,
"children": {
"TrainerController._reset_env": {
"total": 6.6819898849998935,
"count": 1,
"self": 6.6819898849998935
},
"TrainerController.advance": {
"total": 1054.930506734008,
"count": 31705,
"self": 0.7857568269714648,
"children": {
"env_step": {
"total": 742.7545380100102,
"count": 31705,
"self": 684.428435121029,
"children": {
"SubprocessEnvManager._take_step": {
"total": 57.863943221003865,
"count": 31705,
"self": 2.4792560059992184,
"children": {
"TorchPolicy.evaluate": {
"total": 55.38468721500465,
"count": 31325,
"self": 55.38468721500465
}
}
},
"workers": {
"total": 0.46215966797728925,
"count": 31705,
"self": 0.0,
"children": {
"worker_root": {
"total": 1059.9195409480283,
"count": 31705,
"is_parallel": true,
"self": 435.8469882600233,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002547735999996803,
"count": 1,
"is_parallel": true,
"self": 0.0007556589997648189,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017920770002319841,
"count": 8,
"is_parallel": true,
"self": 0.0017920770002319841
}
}
},
"UnityEnvironment.step": {
"total": 0.04570040499993411,
"count": 1,
"is_parallel": true,
"self": 0.0005166009998447407,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000470125999981974,
"count": 1,
"is_parallel": true,
"self": 0.000470125999981974
},
"communicator.exchange": {
"total": 0.043151348000037615,
"count": 1,
"is_parallel": true,
"self": 0.043151348000037615
},
"steps_from_proto": {
"total": 0.0015623300000697782,
"count": 1,
"is_parallel": true,
"self": 0.0003440160002128323,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012183139998569459,
"count": 8,
"is_parallel": true,
"self": 0.0012183139998569459
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 624.072552688005,
"count": 31704,
"is_parallel": true,
"self": 15.841444078962013,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 11.74328116402512,
"count": 31704,
"is_parallel": true,
"self": 11.74328116402512
},
"communicator.exchange": {
"total": 549.7589364910261,
"count": 31704,
"is_parallel": true,
"self": 549.7589364910261
},
"steps_from_proto": {
"total": 46.72889095399171,
"count": 31704,
"is_parallel": true,
"self": 10.117620485966881,
"children": {
"_process_rank_one_or_two_observation": {
"total": 36.61127046802483,
"count": 253632,
"is_parallel": true,
"self": 36.61127046802483
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 311.39021189702646,
"count": 31705,
"self": 1.3202999310308314,
"children": {
"process_trajectory": {
"total": 57.90685148799673,
"count": 31705,
"self": 57.74754467999662,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15930680800011032,
"count": 1,
"self": 0.15930680800011032
}
}
},
"_update_policy": {
"total": 252.1630604779989,
"count": 221,
"self": 160.73096351797892,
"children": {
"TorchPPOOptimizer.update": {
"total": 91.43209696001998,
"count": 11379,
"self": 91.43209696001998
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2629998309421353e-06,
"count": 1,
"self": 1.2629998309421353e-06
},
"TrainerController._save_models": {
"total": 0.13864900099997612,
"count": 1,
"self": 0.0018968489998769655,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13675215200009916,
"count": 1,
"self": 0.13675215200009916
}
}
}
}
}
}
}