OrionChang's picture
First Push
04b2a9e verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.22230564057826996,
"min": 0.2179831713438034,
"max": 1.3764774799346924,
"count": 58
},
"Pyramids.Policy.Entropy.sum": {
"value": 6690.5107421875,
"min": 6570.884765625,
"max": 41756.8203125,
"count": 58
},
"Pyramids.Step.mean": {
"value": 1739951.0,
"min": 29882.0,
"max": 1739951.0,
"count": 58
},
"Pyramids.Step.sum": {
"value": 1739951.0,
"min": 29882.0,
"max": 1739951.0,
"count": 58
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.8026752471923828,
"min": -0.23044979572296143,
"max": 0.8278282880783081,
"count": 58
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 239.99989318847656,
"min": -54.616600036621094,
"max": 241.4636688232422,
"count": 58
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.006733807269483805,
"min": -0.027674255892634392,
"max": 0.4535656273365021,
"count": 58
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 2.0134084224700928,
"min": -7.444375038146973,
"max": 107.49505615234375,
"count": 58
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06919974152513823,
"min": 0.06366072433662512,
"max": 0.0735417628329951,
"count": 58
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9687963813519352,
"min": 0.5147923398309657,
"max": 1.0678551621440064,
"count": 58
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015175669149956104,
"min": 0.0007733120138288904,
"max": 0.016515489673741113,
"count": 58
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.21245936809938545,
"min": 0.008506432152117794,
"max": 0.2477323451061167,
"count": 58
},
"Pyramids.Policy.LearningRate.mean": {
"value": 0.00012756899319130713,
"min": 0.00012756899319130713,
"max": 0.0002984119719579143,
"count": 58
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0017859659046783,
"min": 0.0017859659046783,
"max": 0.004027400057533366,
"count": 58
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.14252297857142862,
"min": 0.14252297857142862,
"max": 0.19947065714285714,
"count": 58
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.9953217000000005,
"min": 1.3962946,
"max": 2.842466633333333,
"count": 58
},
"Pyramids.Policy.Beta.mean": {
"value": 0.004258045559285714,
"min": 0.004258045559285714,
"max": 0.009947118648571427,
"count": 58
},
"Pyramids.Policy.Beta.sum": {
"value": 0.05961263783,
"min": 0.05961263783,
"max": 0.13426241667,
"count": 58
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.008843290619552135,
"min": 0.00824847724288702,
"max": 0.5221182703971863,
"count": 58
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.12380606681108475,
"min": 0.11547867953777313,
"max": 3.6548280715942383,
"count": 58
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 221.5808823529412,
"min": 221.5808823529412,
"max": 995.7241379310345,
"count": 58
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30135.0,
"min": 16553.0,
"max": 33688.0,
"count": 58
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7774592440437387,
"min": -0.9276966041532057,
"max": 1.7774592440437387,
"count": 58
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 239.95699794590473,
"min": -29.24900171160698,
"max": 239.95699794590473,
"count": 58
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7774592440437387,
"min": -0.9276966041532057,
"max": 1.7774592440437387,
"count": 58
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 239.95699794590473,
"min": -29.24900171160698,
"max": 239.95699794590473,
"count": 58
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.02037504119302698,
"min": 0.02037504119302698,
"max": 10.259409879936891,
"count": 58
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.7506305610586423,
"min": 2.5191779543238226,
"max": 174.40996795892715,
"count": 58
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 58
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 58
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1744462307",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1744469390"
},
"total": 7082.598148637,
"count": 1,
"self": 0.6072201229999337,
"children": {
"run_training.setup": {
"total": 0.04248473899860983,
"count": 1,
"self": 0.04248473899860983
},
"TrainerController.start_learning": {
"total": 7081.948443775002,
"count": 1,
"self": 4.780325137087857,
"children": {
"TrainerController._reset_env": {
"total": 5.174224450000111,
"count": 1,
"self": 5.174224450000111
},
"TrainerController.advance": {
"total": 7071.760306634915,
"count": 114610,
"self": 4.931810456733729,
"children": {
"env_step": {
"total": 4869.6852242393325,
"count": 114610,
"self": 4536.926056349148,
"children": {
"SubprocessEnvManager._take_step": {
"total": 329.9899262360159,
"count": 114610,
"self": 15.369478677206644,
"children": {
"TorchPolicy.evaluate": {
"total": 314.62044755880925,
"count": 110575,
"self": 314.62044755880925
}
}
},
"workers": {
"total": 2.7692416541685816,
"count": 114609,
"self": 0.0,
"children": {
"worker_root": {
"total": 7065.881921223372,
"count": 114609,
"is_parallel": true,
"self": 2880.4127369203015,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003186459000062314,
"count": 1,
"is_parallel": true,
"self": 0.001115334998758044,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0020711240013042698,
"count": 8,
"is_parallel": true,
"self": 0.0020711240013042698
}
}
},
"UnityEnvironment.step": {
"total": 0.13023513999905845,
"count": 1,
"is_parallel": true,
"self": 0.0007576279986096779,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004880090000369819,
"count": 1,
"is_parallel": true,
"self": 0.0004880090000369819
},
"communicator.exchange": {
"total": 0.11610472800020943,
"count": 1,
"is_parallel": true,
"self": 0.11610472800020943
},
"steps_from_proto": {
"total": 0.012884775000202353,
"count": 1,
"is_parallel": true,
"self": 0.01073863499732397,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002146140002878383,
"count": 8,
"is_parallel": true,
"self": 0.002146140002878383
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 4185.4691843030705,
"count": 114608,
"is_parallel": true,
"self": 87.12863570607078,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 58.87724772881484,
"count": 114608,
"is_parallel": true,
"self": 58.87724772881484
},
"communicator.exchange": {
"total": 3793.664607224686,
"count": 114608,
"is_parallel": true,
"self": 3793.664607224686
},
"steps_from_proto": {
"total": 245.79869364349906,
"count": 114608,
"is_parallel": true,
"self": 53.90631099178427,
"children": {
"_process_rank_one_or_two_observation": {
"total": 191.8923826517148,
"count": 916864,
"is_parallel": true,
"self": 191.8923826517148
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 2197.1432719388486,
"count": 114609,
"self": 9.329065480476856,
"children": {
"process_trajectory": {
"total": 331.4411001483895,
"count": 114609,
"self": 331.04177792238806,
"children": {
"RLTrainer._checkpoint": {
"total": 0.39932222600145906,
"count": 3,
"self": 0.39932222600145906
}
}
},
"_update_policy": {
"total": 1856.3731063099822,
"count": 820,
"self": 722.7935800892028,
"children": {
"TorchPPOOptimizer.update": {
"total": 1133.5795262207794,
"count": 40362,
"self": 1133.5795262207794
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.7569982446730137e-06,
"count": 1,
"self": 1.7569982446730137e-06
},
"TrainerController._save_models": {
"total": 0.23358579600062512,
"count": 1,
"self": 0.0030260180010373006,
"children": {
"RLTrainer._checkpoint": {
"total": 0.23055977799958782,
"count": 1,
"self": 0.23055977799958782
}
}
}
}
}
}
}