testpyramidsrnd / run_logs /timers.json
bguan's picture
First Pyramids
aea05d6
raw
history blame
19.1 kB
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.7434133887290955,
"min": 0.7434133887290955,
"max": 1.4159648418426514,
"count": 16
},
"Pyramids.Policy.Entropy.sum": {
"value": 22314.296875,
"min": 22314.296875,
"max": 42954.7109375,
"count": 16
},
"Pyramids.Step.mean": {
"value": 479963.0,
"min": 29952.0,
"max": 479963.0,
"count": 16
},
"Pyramids.Step.sum": {
"value": 479963.0,
"min": 29952.0,
"max": 479963.0,
"count": 16
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.06252362579107285,
"min": -0.09519326686859131,
"max": 0.12882977724075317,
"count": 16
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -15.193241119384766,
"min": -22.941577911376953,
"max": 30.532657623291016,
"count": 16
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.016554778441786766,
"min": 0.016554778441786766,
"max": 0.2520255148410797,
"count": 16
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 4.022810935974121,
"min": 4.022810935974121,
"max": 60.486122131347656,
"count": 16
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06603587224326153,
"min": 0.06573693719203783,
"max": 0.07239651848596565,
"count": 16
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9245022114056614,
"min": 0.4986174256414049,
"max": 0.9765913942373746,
"count": 16
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.0033305518411907826,
"min": 9.622271728143443e-05,
"max": 0.004109752835040264,
"count": 16
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.04662772577667096,
"min": 0.001347118041940082,
"max": 0.04662772577667096,
"count": 16
},
"Pyramids.Policy.LearningRate.mean": {
"value": 2.09514930162e-05,
"min": 2.09514930162e-05,
"max": 0.00029030126037577137,
"count": 16
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0002933209022268,
"min": 0.0002933209022268,
"max": 0.0030625369791543993,
"count": 16
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1069838,
"min": 0.1069838,
"max": 0.19676708571428575,
"count": 16
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4977732000000001,
"min": 1.3382272,
"max": 2.254682,
"count": 16
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0007076816200000001,
"min": 0.0007076816200000001,
"max": 0.00967703186285714,
"count": 16
},
"Pyramids.Policy.Beta.sum": {
"value": 0.00990754268,
"min": 0.00990754268,
"max": 0.10210247543999999,
"count": 16
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01608044095337391,
"min": 0.01608044095337391,
"max": 0.2806084454059601,
"count": 16
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.22512616217136383,
"min": 0.22512616217136383,
"max": 1.9642590284347534,
"count": 16
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 936.4242424242424,
"min": 903.9411764705883,
"max": 999.0,
"count": 16
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30902.0,
"min": 15984.0,
"max": 32644.0,
"count": 16
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -0.5126788327188203,
"min": -1.0000000521540642,
"max": -0.5126788327188203,
"count": 16
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -16.91840147972107,
"min": -32.000001668930054,
"max": -13.530801147222519,
"count": 16
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -0.5126788327188203,
"min": -1.0000000521540642,
"max": -0.5126788327188203,
"count": 16
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -16.91840147972107,
"min": -32.000001668930054,
"max": -13.530801147222519,
"count": 16
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.15698340889348678,
"min": 0.15698340889348678,
"max": 5.1650382513180375,
"count": 16
},
"Pyramids.Policy.RndReward.sum": {
"value": 5.180452493485063,
"min": 5.180452493485063,
"max": 82.6406120210886,
"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": "1660874730",
"python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1660875895"
},
"total": 1164.9212725590005,
"count": 1,
"self": 0.53649120900036,
"children": {
"run_training.setup": {
"total": 0.0632450059997609,
"count": 1,
"self": 0.0632450059997609
},
"TrainerController.start_learning": {
"total": 1164.3215363440004,
"count": 1,
"self": 0.8257684760678785,
"children": {
"TrainerController._reset_env": {
"total": 10.570688660000087,
"count": 1,
"self": 10.570688660000087
},
"TrainerController.advance": {
"total": 1152.8096506279321,
"count": 31520,
"self": 0.9037352339619247,
"children": {
"env_step": {
"total": 706.6603270160099,
"count": 31520,
"self": 633.3907426699984,
"children": {
"SubprocessEnvManager._take_step": {
"total": 72.84539202202359,
"count": 31520,
"self": 3.012815553167002,
"children": {
"TorchPolicy.evaluate": {
"total": 69.83257646885659,
"count": 31330,
"self": 24.59598348594318,
"children": {
"TorchPolicy.sample_actions": {
"total": 45.23659298291341,
"count": 31330,
"self": 45.23659298291341
}
}
}
}
},
"workers": {
"total": 0.42419232398788154,
"count": 31520,
"self": 0.0,
"children": {
"worker_root": {
"total": 1161.9478368390428,
"count": 31520,
"is_parallel": true,
"self": 592.0339420101022,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0063251360002141155,
"count": 1,
"is_parallel": true,
"self": 0.004704239001057431,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016208969991566846,
"count": 8,
"is_parallel": true,
"self": 0.0016208969991566846
}
}
},
"UnityEnvironment.step": {
"total": 0.06018109600017851,
"count": 1,
"is_parallel": true,
"self": 0.0006120319999354251,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000661209000099916,
"count": 1,
"is_parallel": true,
"self": 0.000661209000099916
},
"communicator.exchange": {
"total": 0.05644909800003006,
"count": 1,
"is_parallel": true,
"self": 0.05644909800003006
},
"steps_from_proto": {
"total": 0.00245875700011311,
"count": 1,
"is_parallel": true,
"self": 0.0008858399996825028,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001572917000430607,
"count": 8,
"is_parallel": true,
"self": 0.001572917000430607
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 569.9138948289406,
"count": 31519,
"is_parallel": true,
"self": 16.649241480894034,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 15.647940984973502,
"count": 31519,
"is_parallel": true,
"self": 15.647940984973502
},
"communicator.exchange": {
"total": 476.543193222029,
"count": 31519,
"is_parallel": true,
"self": 476.543193222029
},
"steps_from_proto": {
"total": 61.07351914104402,
"count": 31519,
"is_parallel": true,
"self": 16.48834020427512,
"children": {
"_process_rank_one_or_two_observation": {
"total": 44.5851789367689,
"count": 252152,
"is_parallel": true,
"self": 44.5851789367689
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 445.2455883779603,
"count": 31520,
"self": 1.1812028509043557,
"children": {
"process_trajectory": {
"total": 99.40918557506484,
"count": 31520,
"self": 98.2335272090645,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1756583660003344,
"count": 10,
"self": 1.1756583660003344
}
}
},
"_update_policy": {
"total": 344.6551999519911,
"count": 207,
"self": 124.77479632408995,
"children": {
"TorchPPOOptimizer.update": {
"total": 219.88040362790116,
"count": 11472,
"self": 219.88040362790116
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1670008461805992e-06,
"count": 1,
"self": 1.1670008461805992e-06
},
"TrainerController._save_models": {
"total": 0.11542741299945192,
"count": 1,
"self": 0.0018925759986814228,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1135348370007705,
"count": 1,
"self": 0.1135348370007705
}
}
}
}
}
}
}