Tseaver's picture
First Push
0ffc757
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5678761005401611,
"min": 0.5670034885406494,
"max": 1.421993613243103,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 16981.767578125,
"min": 16981.767578125,
"max": 43137.59765625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989886.0,
"min": 29952.0,
"max": 989886.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989886.0,
"min": 29952.0,
"max": 989886.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.33195415139198303,
"min": -0.10788492858409882,
"max": 0.41560491919517517,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 86.3080825805664,
"min": -25.892383575439453,
"max": 112.6289291381836,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.007902049459517002,
"min": -0.011736652813851833,
"max": 0.4033971130847931,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 2.054532766342163,
"min": -2.887216567993164,
"max": 95.60511779785156,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06619814978391539,
"min": 0.06455615392040422,
"max": 0.07375084292100043,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9267740969748155,
"min": 0.5000791722659729,
"max": 1.0834041273303552,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.013679937184641956,
"min": 6.737575528443768e-05,
"max": 0.013967199561516958,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.19151912058498738,
"min": 0.0009432605739821276,
"max": 0.2089738339733837,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.334411840942856e-06,
"min": 7.334411840942856e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010268176577319999,
"min": 0.00010268176577319999,
"max": 0.0033821594726135998,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10244477142857142,
"min": 0.10244477142857142,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4342267999999998,
"min": 1.3886848,
"max": 2.5273864,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002542326657142858,
"min": 0.0002542326657142858,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003559257320000001,
"min": 0.003559257320000001,
"max": 0.11276590135999999,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.014242283068597317,
"min": 0.014242283068597317,
"max": 0.47914355993270874,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.19939196109771729,
"min": 0.19939196109771729,
"max": 3.3540048599243164,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 458.0,
"min": 435.5342465753425,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 27938.0,
"min": 15984.0,
"max": 32114.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.2140655512692498,
"min": -1.0000000521540642,
"max": 1.423691873111435,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 74.05799862742424,
"min": -31.996801659464836,
"max": 105.35319861024618,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.2140655512692498,
"min": -1.0000000521540642,
"max": 1.423691873111435,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 74.05799862742424,
"min": -31.996801659464836,
"max": 105.35319861024618,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.06755750842731671,
"min": 0.0658381881530167,
"max": 10.457255099900067,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.1210080140663194,
"min": 4.1210080140663194,
"max": 167.31608159840107,
"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": "1687546544",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1687548866"
},
"total": 2322.3891790810003,
"count": 1,
"self": 0.5786994300001425,
"children": {
"run_training.setup": {
"total": 0.038552283000058196,
"count": 1,
"self": 0.038552283000058196
},
"TrainerController.start_learning": {
"total": 2321.771927368,
"count": 1,
"self": 1.6348752390513255,
"children": {
"TrainerController._reset_env": {
"total": 4.337373200000002,
"count": 1,
"self": 4.337373200000002
},
"TrainerController.advance": {
"total": 2315.6887360269484,
"count": 63419,
"self": 1.6188138959983007,
"children": {
"env_step": {
"total": 1645.5519022459596,
"count": 63419,
"self": 1520.1467088389752,
"children": {
"SubprocessEnvManager._take_step": {
"total": 124.49933804801037,
"count": 63419,
"self": 5.197448378013405,
"children": {
"TorchPolicy.evaluate": {
"total": 119.30188966999697,
"count": 62551,
"self": 119.30188966999697
}
}
},
"workers": {
"total": 0.9058553589740086,
"count": 63419,
"self": 0.0,
"children": {
"worker_root": {
"total": 2316.071308166972,
"count": 63419,
"is_parallel": true,
"self": 920.510646013021,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017227870000624534,
"count": 1,
"is_parallel": true,
"self": 0.0005163020001646146,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012064849998978389,
"count": 8,
"is_parallel": true,
"self": 0.0012064849998978389
}
}
},
"UnityEnvironment.step": {
"total": 0.05043913899999097,
"count": 1,
"is_parallel": true,
"self": 0.000563800000008996,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005634030000010171,
"count": 1,
"is_parallel": true,
"self": 0.0005634030000010171
},
"communicator.exchange": {
"total": 0.04737711400002809,
"count": 1,
"is_parallel": true,
"self": 0.04737711400002809
},
"steps_from_proto": {
"total": 0.0019348219999528737,
"count": 1,
"is_parallel": true,
"self": 0.0004200649998438166,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015147570001090571,
"count": 8,
"is_parallel": true,
"self": 0.0015147570001090571
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1395.560662153951,
"count": 63418,
"is_parallel": true,
"self": 35.6409804658806,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.809848014053614,
"count": 63418,
"is_parallel": true,
"self": 23.809848014053614
},
"communicator.exchange": {
"total": 1228.527356831029,
"count": 63418,
"is_parallel": true,
"self": 1228.527356831029
},
"steps_from_proto": {
"total": 107.58247684298783,
"count": 63418,
"is_parallel": true,
"self": 21.451763238871763,
"children": {
"_process_rank_one_or_two_observation": {
"total": 86.13071360411607,
"count": 507344,
"is_parallel": true,
"self": 86.13071360411607
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 668.5180198849906,
"count": 63419,
"self": 2.855346056976714,
"children": {
"process_trajectory": {
"total": 111.14083978501435,
"count": 63419,
"self": 110.87202376801429,
"children": {
"RLTrainer._checkpoint": {
"total": 0.26881601700006286,
"count": 2,
"self": 0.26881601700006286
}
}
},
"_update_policy": {
"total": 554.5218340429996,
"count": 445,
"self": 352.5842217679548,
"children": {
"TorchPPOOptimizer.update": {
"total": 201.93761227504478,
"count": 22851,
"self": 201.93761227504478
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1980000635958277e-06,
"count": 1,
"self": 1.1980000635958277e-06
},
"TrainerController._save_models": {
"total": 0.1109417040001972,
"count": 1,
"self": 0.0016141880000759556,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10932751600012125,
"count": 1,
"self": 0.10932751600012125
}
}
}
}
}
}
}