Cloud1989's picture
First Push
c0a3cff
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.12708690762519836,
"min": 0.11876944452524185,
"max": 1.3915067911148071,
"count": 100
},
"Pyramids.Policy.Entropy.sum": {
"value": 3832.94091796875,
"min": 3525.0771484375,
"max": 42212.75,
"count": 100
},
"Pyramids.Step.mean": {
"value": 2999941.0,
"min": 29952.0,
"max": 2999941.0,
"count": 100
},
"Pyramids.Step.sum": {
"value": 2999941.0,
"min": 29952.0,
"max": 2999941.0,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.8504750728607178,
"min": -0.10110758244991302,
"max": 0.9263685941696167,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 257.6939392089844,
"min": -24.366928100585938,
"max": 289.953369140625,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.005507778376340866,
"min": -0.02369612082839012,
"max": 0.5726029276847839,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 1.6688568592071533,
"min": -7.322101593017578,
"max": 135.70689392089844,
"count": 100
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06727806884529335,
"min": 0.06492168600848715,
"max": 0.07466189914395929,
"count": 100
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9418929638341069,
"min": 0.489267415471941,
"max": 1.1199284871593893,
"count": 100
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.013917682934940485,
"min": 0.0008999599888638763,
"max": 0.014746523209391307,
"count": 100
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.1948475610891668,
"min": 0.008728186449258211,
"max": 0.2064513249314783,
"count": 100
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.5584637662595208e-06,
"min": 1.5584637662595208e-06,
"max": 0.00029838354339596195,
"count": 100
},
"Pyramids.Policy.LearningRate.sum": {
"value": 2.1818492727633292e-05,
"min": 2.1818492727633292e-05,
"max": 0.003969126876957733,
"count": 100
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10051945476190478,
"min": 0.10051945476190478,
"max": 0.19946118095238097,
"count": 100
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4072723666666669,
"min": 1.3897045333333333,
"max": 2.812596966666667,
"count": 100
},
"Pyramids.Policy.Beta.mean": {
"value": 6.189353071428559e-05,
"min": 6.189353071428559e-05,
"max": 0.009946171977142856,
"count": 100
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0008665094299999982,
"min": 0.0008665094299999982,
"max": 0.13231192244,
"count": 100
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.00781369861215353,
"min": 0.007554124109447002,
"max": 0.4967724680900574,
"count": 100
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.10939178615808487,
"min": 0.10575773566961288,
"max": 3.477407217025757,
"count": 100
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 227.92537313432837,
"min": 196.43506493506493,
"max": 999.0,
"count": 100
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30542.0,
"min": 15984.0,
"max": 33525.0,
"count": 100
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7426955066621304,
"min": -1.0000000521540642,
"max": 1.803564924891893,
"count": 100
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 233.52119789272547,
"min": -32.000001668930054,
"max": 277.7489984333515,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7426955066621304,
"min": -1.0000000521540642,
"max": 1.803564924891893,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 233.52119789272547,
"min": -32.000001668930054,
"max": 277.7489984333515,
"count": 100
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.018485499473606625,
"min": 0.016004074810482122,
"max": 9.971173647791147,
"count": 100
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.477056929463288,
"min": 2.281594998057699,
"max": 159.53877836465836,
"count": 100
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1704512176",
"python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]",
"command_line_arguments": "\\\\?\\C:\\Users\\Alienware\\AppData\\Roaming\\Python\\Python310\\Scripts\\mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/windows/pyramids/Pyramids.exe --run-id=PyramidsTraining --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.2+cpu",
"numpy_version": "1.23.5",
"end_time_seconds": "1704518818"
},
"total": 6642.65068150009,
"count": 1,
"self": 991.3381159999408,
"children": {
"run_training.setup": {
"total": 0.09633590001612902,
"count": 1,
"self": 0.09633590001612902
},
"TrainerController.start_learning": {
"total": 5651.216229600133,
"count": 1,
"self": 4.661145612830296,
"children": {
"TrainerController._reset_env": {
"total": 4.688702899962664,
"count": 1,
"self": 4.688702899962664
},
"TrainerController.advance": {
"total": 5641.7983834873885,
"count": 195768,
"self": 4.185639354400337,
"children": {
"env_step": {
"total": 2799.7124221110716,
"count": 195768,
"self": 2486.6782490678597,
"children": {
"SubprocessEnvManager._take_step": {
"total": 309.99192151939496,
"count": 195768,
"self": 12.21241666120477,
"children": {
"TorchPolicy.evaluate": {
"total": 297.7795048581902,
"count": 187562,
"self": 297.7795048581902
}
}
},
"workers": {
"total": 3.042251523816958,
"count": 195768,
"self": 0.0,
"children": {
"worker_root": {
"total": 5640.408113432815,
"count": 195768,
"is_parallel": true,
"self": 3488.827363583725,
"children": {
"steps_from_proto": {
"total": 0.00121380016207695,
"count": 1,
"is_parallel": true,
"self": 0.0003548001404851675,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008590000215917826,
"count": 8,
"is_parallel": true,
"self": 0.0008590000215917826
}
}
},
"UnityEnvironment.step": {
"total": 2151.5795360489283,
"count": 195768,
"is_parallel": true,
"self": 70.3655079039745,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 63.13015302387066,
"count": 195768,
"is_parallel": true,
"self": 63.13015302387066
},
"communicator.exchange": {
"total": 1805.0613140263595,
"count": 195768,
"is_parallel": true,
"self": 1805.0613140263595
},
"steps_from_proto": {
"total": 213.02256109472364,
"count": 195768,
"is_parallel": true,
"self": 47.50721585727297,
"children": {
"_process_rank_one_or_two_observation": {
"total": 165.51534523745067,
"count": 1566144,
"is_parallel": true,
"self": 165.51534523745067
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 2837.9003220219165,
"count": 195768,
"self": 8.730945472605526,
"children": {
"process_trajectory": {
"total": 417.65641144826077,
"count": 195768,
"self": 417.1554317479022,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5009797003585845,
"count": 6,
"self": 0.5009797003585845
}
}
},
"_update_policy": {
"total": 2411.51296510105,
"count": 1395,
"self": 1088.8201897889376,
"children": {
"TorchPPOOptimizer.update": {
"total": 1322.6927753121126,
"count": 68478,
"self": 1322.6927753121126
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.200009137392044e-06,
"count": 1,
"self": 1.200009137392044e-06
},
"TrainerController._save_models": {
"total": 0.0679963999427855,
"count": 1,
"self": 0.002037599915638566,
"children": {
"RLTrainer._checkpoint": {
"total": 0.06595880002714694,
"count": 1,
"self": 0.06595880002714694
}
}
}
}
}
}
}