azetaaa's picture
Init
14f11b1
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4337383210659027,
"min": 0.4337383210659027,
"max": 1.4918110370635986,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 13116.2470703125,
"min": 13116.2470703125,
"max": 45255.578125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989968.0,
"min": 29930.0,
"max": 989968.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989968.0,
"min": 29930.0,
"max": 989968.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.44585588574409485,
"min": -0.15662716329097748,
"max": 0.44585588574409485,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 119.04351806640625,
"min": -37.120635986328125,
"max": 119.04351806640625,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.10897796601057053,
"min": -0.06121215969324112,
"max": 0.12376759946346283,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 29.097116470336914,
"min": -14.507282257080078,
"max": 29.827991485595703,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06737141665750339,
"min": 0.06563936169725564,
"max": 0.07412165388981437,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9431998332050474,
"min": 0.5188515772287006,
"max": 1.0536211827129593,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.013742638688113184,
"min": 8.522455670903962e-05,
"max": 0.018146761162238866,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.1923969416335846,
"min": 0.0011079192372175151,
"max": 0.272201417433583,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.279833287707143e-06,
"min": 7.279833287707143e-06,
"max": 0.0002952338587315714,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010191766602790001,
"min": 0.00010191766602790001,
"max": 0.003507665930778099,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10242657857142859,
"min": 0.10242657857142859,
"max": 0.1984112857142857,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4339721000000003,
"min": 1.388879,
"max": 2.5692218999999996,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025241519928571437,
"min": 0.00025241519928571437,
"max": 0.009841287442857142,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0035338127900000015,
"min": 0.0035338127900000015,
"max": 0.11694526780999999,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.008856919594109058,
"min": 0.008856919594109058,
"max": 0.3046390414237976,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.12399686872959137,
"min": 0.12399686872959137,
"max": 2.1324732303619385,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 433.63235294117646,
"min": 418.88,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29487.0,
"min": 16601.0,
"max": 33360.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.360423507716726,
"min": -0.9999161809682846,
"max": 1.4477413137753805,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 92.50879852473736,
"min": -31.99640166759491,
"max": 108.58059853315353,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.360423507716726,
"min": -0.9999161809682846,
"max": 1.4477413137753805,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 92.50879852473736,
"min": -31.99640166759491,
"max": 108.58059853315353,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.03990201674733886,
"min": 0.03990201674733886,
"max": 5.869599439642009,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.7133371388190426,
"min": 2.699884009620291,
"max": 99.78319047391415,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1684872832",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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=Pyramids1 --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": "1684875012"
},
"total": 2179.756273581,
"count": 1,
"self": 0.4844420920007906,
"children": {
"run_training.setup": {
"total": 0.03787803199975315,
"count": 1,
"self": 0.03787803199975315
},
"TrainerController.start_learning": {
"total": 2179.2339534569996,
"count": 1,
"self": 1.5980866138515921,
"children": {
"TrainerController._reset_env": {
"total": 3.808881525000288,
"count": 1,
"self": 3.808881525000288
},
"TrainerController.advance": {
"total": 2173.7335163761486,
"count": 63493,
"self": 1.533615075234593,
"children": {
"env_step": {
"total": 1540.8780514329187,
"count": 63493,
"self": 1423.4998636568998,
"children": {
"SubprocessEnvManager._take_step": {
"total": 116.4209846790568,
"count": 63493,
"self": 5.038311054027417,
"children": {
"TorchPolicy.evaluate": {
"total": 111.38267362502938,
"count": 62556,
"self": 111.38267362502938
}
}
},
"workers": {
"total": 0.9572030969620755,
"count": 63493,
"self": 0.0,
"children": {
"worker_root": {
"total": 2173.8215945880575,
"count": 63493,
"is_parallel": true,
"self": 867.4509433140297,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018925609997495485,
"count": 1,
"is_parallel": true,
"self": 0.0005738489981013117,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013187120016482368,
"count": 8,
"is_parallel": true,
"self": 0.0013187120016482368
}
}
},
"UnityEnvironment.step": {
"total": 0.047110194000197225,
"count": 1,
"is_parallel": true,
"self": 0.0005654240003423183,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004959019997841096,
"count": 1,
"is_parallel": true,
"self": 0.0004959019997841096
},
"communicator.exchange": {
"total": 0.044200040999839985,
"count": 1,
"is_parallel": true,
"self": 0.044200040999839985
},
"steps_from_proto": {
"total": 0.0018488270002308127,
"count": 1,
"is_parallel": true,
"self": 0.0003762890000871266,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001472538000143686,
"count": 8,
"is_parallel": true,
"self": 0.001472538000143686
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1306.3706512740278,
"count": 63492,
"is_parallel": true,
"self": 31.988922692019514,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.669859730992812,
"count": 63492,
"is_parallel": true,
"self": 22.669859730992812
},
"communicator.exchange": {
"total": 1152.44658497099,
"count": 63492,
"is_parallel": true,
"self": 1152.44658497099
},
"steps_from_proto": {
"total": 99.26528388002544,
"count": 63492,
"is_parallel": true,
"self": 20.64709789198423,
"children": {
"_process_rank_one_or_two_observation": {
"total": 78.6181859880412,
"count": 507936,
"is_parallel": true,
"self": 78.6181859880412
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 631.3218498679953,
"count": 63493,
"self": 2.92274139897836,
"children": {
"process_trajectory": {
"total": 106.33729536402416,
"count": 63493,
"self": 106.12773656502395,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2095587990002059,
"count": 2,
"self": 0.2095587990002059
}
}
},
"_update_policy": {
"total": 522.0618131049928,
"count": 451,
"self": 335.5395029949391,
"children": {
"TorchPPOOptimizer.update": {
"total": 186.5223101100537,
"count": 22824,
"self": 186.5223101100537
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0869998732232489e-06,
"count": 1,
"self": 1.0869998732232489e-06
},
"TrainerController._save_models": {
"total": 0.09346785499928956,
"count": 1,
"self": 0.0015165619988692924,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09195129300042026,
"count": 1,
"self": 0.09195129300042026
}
}
}
}
}
}
}