proleetops's picture
First Push
55c2d98
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.24686159193515778,
"min": 0.24686159193515778,
"max": 1.42119562625885,
"count": 62
},
"Pyramids.Policy.Entropy.sum": {
"value": 7425.5966796875,
"min": 7425.5966796875,
"max": 43113.390625,
"count": 62
},
"Pyramids.Step.mean": {
"value": 1859890.0,
"min": 29952.0,
"max": 1859890.0,
"count": 62
},
"Pyramids.Step.sum": {
"value": 1859890.0,
"min": 29952.0,
"max": 1859890.0,
"count": 62
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.7776249051094055,
"min": -0.09688938409090042,
"max": 0.8463770151138306,
"count": 62
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 229.39935302734375,
"min": -23.350341796875,
"max": 257.906005859375,
"count": 62
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.012212756089866161,
"min": -0.013315688818693161,
"max": 0.4127585291862488,
"count": 62
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 3.6027631759643555,
"min": -3.83491849899292,
"max": 97.82376861572266,
"count": 62
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06973542186911107,
"min": 0.06404630537491314,
"max": 0.07343915589375512,
"count": 62
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.976295906167555,
"min": 0.49957402264960277,
"max": 1.0893833109476676,
"count": 62
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.013424168699116093,
"min": 0.0009904792794348614,
"max": 0.018852772830065253,
"count": 62
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.1879383617876253,
"min": 0.01386670991208806,
"max": 0.26393881962091353,
"count": 62
},
"Pyramids.Policy.LearningRate.mean": {
"value": 0.00011554885434087856,
"min": 0.00011554885434087856,
"max": 0.00029838354339596195,
"count": 62
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0016176839607722998,
"min": 0.0016176839607722998,
"max": 0.004012035262654933,
"count": 62
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.13851626428571429,
"min": 0.13851626428571429,
"max": 0.19946118095238097,
"count": 62
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.9392277,
"min": 1.3962282666666668,
"max": 2.7975673333333333,
"count": 62
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0038577748021428574,
"min": 0.0038577748021428574,
"max": 0.009946171977142856,
"count": 62
},
"Pyramids.Policy.Beta.sum": {
"value": 0.054008847230000004,
"min": 0.054008847230000004,
"max": 0.13374077216,
"count": 62
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.006090694572776556,
"min": 0.005872331093996763,
"max": 0.4922802448272705,
"count": 62
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.08526972681283951,
"min": 0.08221263438463211,
"max": 3.4459617137908936,
"count": 62
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 255.44628099173553,
"min": 222.984375,
"max": 999.0,
"count": 62
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30909.0,
"min": 15984.0,
"max": 32687.0,
"count": 62
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7280198245748015,
"min": -1.0000000521540642,
"max": 1.7771968423850892,
"count": 62
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 209.090398773551,
"min": -28.71800173074007,
"max": 232.01999866962433,
"count": 62
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7280198245748015,
"min": -1.0000000521540642,
"max": 1.7771968423850892,
"count": 62
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 209.090398773551,
"min": -28.71800173074007,
"max": 232.01999866962433,
"count": 62
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.015987653088002332,
"min": 0.014749317220689374,
"max": 9.495187505148351,
"count": 62
},
"Pyramids.Policy.RndReward.sum": {
"value": 1.9345060236482823,
"min": 1.819642380973164,
"max": 151.92300008237362,
"count": 62
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 62
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 62
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1679715212",
"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": "1679719843"
},
"total": 4630.522494276999,
"count": 1,
"self": 0.4933078529984414,
"children": {
"run_training.setup": {
"total": 0.1893598770002427,
"count": 1,
"self": 0.1893598770002427
},
"TrainerController.start_learning": {
"total": 4629.8398265470005,
"count": 1,
"self": 3.1327488288861787,
"children": {
"TrainerController._reset_env": {
"total": 6.793798844999856,
"count": 1,
"self": 6.793798844999856
},
"TrainerController.advance": {
"total": 4619.910574057114,
"count": 121803,
"self": 3.0973786327112975,
"children": {
"env_step": {
"total": 3392.313939282298,
"count": 121803,
"self": 3164.200538931403,
"children": {
"SubprocessEnvManager._take_step": {
"total": 226.23402175093088,
"count": 121803,
"self": 9.241491379109902,
"children": {
"TorchPolicy.evaluate": {
"total": 216.99253037182098,
"count": 117681,
"self": 216.99253037182098
}
}
},
"workers": {
"total": 1.879378599964184,
"count": 121802,
"self": 0.0,
"children": {
"worker_root": {
"total": 4619.223030202877,
"count": 121802,
"is_parallel": true,
"self": 1697.9177683158364,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0031517969996457396,
"count": 1,
"is_parallel": true,
"self": 0.0007609619997310801,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0023908349999146594,
"count": 8,
"is_parallel": true,
"self": 0.0023908349999146594
}
}
},
"UnityEnvironment.step": {
"total": 0.047465385000123206,
"count": 1,
"is_parallel": true,
"self": 0.0005441900002551847,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00047603999973944155,
"count": 1,
"is_parallel": true,
"self": 0.00047603999973944155
},
"communicator.exchange": {
"total": 0.04490423600009308,
"count": 1,
"is_parallel": true,
"self": 0.04490423600009308
},
"steps_from_proto": {
"total": 0.001540919000035501,
"count": 1,
"is_parallel": true,
"self": 0.00036532400008582044,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011755949999496806,
"count": 8,
"is_parallel": true,
"self": 0.0011755949999496806
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 2921.305261887041,
"count": 121801,
"is_parallel": true,
"self": 61.71427607509759,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 44.49756594802011,
"count": 121801,
"is_parallel": true,
"self": 44.49756594802011
},
"communicator.exchange": {
"total": 2633.039174700904,
"count": 121801,
"is_parallel": true,
"self": 2633.039174700904
},
"steps_from_proto": {
"total": 182.05424516301946,
"count": 121801,
"is_parallel": true,
"self": 40.18319733577573,
"children": {
"_process_rank_one_or_two_observation": {
"total": 141.87104782724373,
"count": 974408,
"is_parallel": true,
"self": 141.87104782724373
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1224.4992561421045,
"count": 121802,
"self": 5.872349099243365,
"children": {
"process_trajectory": {
"total": 232.8269802658565,
"count": 121802,
"self": 232.53154363085605,
"children": {
"RLTrainer._checkpoint": {
"total": 0.29543663500044204,
"count": 3,
"self": 0.29543663500044204
}
}
},
"_update_policy": {
"total": 985.7999267770047,
"count": 875,
"self": 628.8231613951039,
"children": {
"TorchPPOOptimizer.update": {
"total": 356.9767653819008,
"count": 42900,
"self": 356.9767653819008
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3879998732591048e-06,
"count": 1,
"self": 1.3879998732591048e-06
},
"TrainerController._save_models": {
"total": 0.002703428001041175,
"count": 1,
"self": 2.2857002477394417e-05,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0026805709985637804,
"count": 1,
"self": 0.0026805709985637804
}
}
}
}
}
}
}