afos950's picture
Second Push
be7d1fb
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5158228278160095,
"min": 0.48265454173088074,
"max": 1.4551777839660645,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 15540.7109375,
"min": 14571.150390625,
"max": 44144.2734375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989982.0,
"min": 29952.0,
"max": 989982.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989982.0,
"min": 29952.0,
"max": 989982.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.33319228887557983,
"min": -0.3030071556568146,
"max": 0.33319228887557983,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 86.96318817138672,
"min": -71.81269836425781,
"max": 86.96318817138672,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.01892361231148243,
"min": 0.001947049517184496,
"max": 0.26130783557891846,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 4.939062595367432,
"min": 0.4926035404205322,
"max": 62.975189208984375,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06784048845131312,
"min": 0.06352640107146146,
"max": 0.07282166642939394,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0176073267696968,
"min": 0.49942116319013213,
"max": 1.0445919664075607,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.012630880057501296,
"min": 0.0003092448813287118,
"max": 0.01310194144614451,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.18946320086251944,
"min": 0.00340169369461583,
"max": 0.18946320086251944,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.486357504580001e-06,
"min": 7.486357504580001e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001122953625687,
"min": 0.0001122953625687,
"max": 0.003374934175022,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10249542000000003,
"min": 0.10249542000000003,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5374313000000004,
"min": 1.3886848,
"max": 2.4861502000000004,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025929245800000006,
"min": 0.00025929245800000006,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0038893868700000007,
"min": 0.0038893868700000007,
"max": 0.1125153022,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.011628476902842522,
"min": 0.011628476902842522,
"max": 0.36218634247779846,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.17442715167999268,
"min": 0.17442715167999268,
"max": 2.535304307937622,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 539.7678571428571,
"min": 494.1896551724138,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30227.0,
"min": 15984.0,
"max": 33061.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.1387213983439974,
"min": -1.0000000521540642,
"max": 1.2988413524781834,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 63.76839830726385,
"min": -30.99780160188675,
"max": 75.33279844373465,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.1387213983439974,
"min": -1.0000000521540642,
"max": 1.2988413524781834,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 63.76839830726385,
"min": -30.99780160188675,
"max": 75.33279844373465,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.06546846600187044,
"min": 0.06546846600187044,
"max": 6.700608023442328,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.666234096104745,
"min": 3.666234096104745,
"max": 107.20972837507725,
"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": "1684331700",
"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=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": "1684335061"
},
"total": 3361.46705027,
"count": 1,
"self": 0.5841340619999755,
"children": {
"run_training.setup": {
"total": 0.05442444799996338,
"count": 1,
"self": 0.05442444799996338
},
"TrainerController.start_learning": {
"total": 3360.82849176,
"count": 1,
"self": 2.272037733970592,
"children": {
"TrainerController._reset_env": {
"total": 1.032731467000076,
"count": 1,
"self": 1.032731467000076
},
"TrainerController.advance": {
"total": 3357.417286294029,
"count": 63474,
"self": 2.4347749989169643,
"children": {
"env_step": {
"total": 2165.3059251730583,
"count": 63474,
"self": 2017.8541175401306,
"children": {
"SubprocessEnvManager._take_step": {
"total": 146.02606217690004,
"count": 63474,
"self": 7.427365240894005,
"children": {
"TorchPolicy.evaluate": {
"total": 138.59869693600604,
"count": 62563,
"self": 138.59869693600604
}
}
},
"workers": {
"total": 1.4257454560276983,
"count": 63474,
"self": 0.0,
"children": {
"worker_root": {
"total": 3353.5193614950167,
"count": 63474,
"is_parallel": true,
"self": 1513.2573826600865,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0027748150000661553,
"count": 1,
"is_parallel": true,
"self": 0.0008819629997560696,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018928520003100857,
"count": 8,
"is_parallel": true,
"self": 0.0018928520003100857
}
}
},
"UnityEnvironment.step": {
"total": 0.07203219300004093,
"count": 1,
"is_parallel": true,
"self": 0.0007003079999776674,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005724239999835845,
"count": 1,
"is_parallel": true,
"self": 0.0005724239999835845
},
"communicator.exchange": {
"total": 0.06849190999992061,
"count": 1,
"is_parallel": true,
"self": 0.06849190999992061
},
"steps_from_proto": {
"total": 0.0022675510001590737,
"count": 1,
"is_parallel": true,
"self": 0.0004464470002858434,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018211039998732304,
"count": 8,
"is_parallel": true,
"self": 0.0018211039998732304
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1840.2619788349302,
"count": 63473,
"is_parallel": true,
"self": 46.18761435086344,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 26.588040818936406,
"count": 63473,
"is_parallel": true,
"self": 26.588040818936406
},
"communicator.exchange": {
"total": 1628.2077655080225,
"count": 63473,
"is_parallel": true,
"self": 1628.2077655080225
},
"steps_from_proto": {
"total": 139.2785581571079,
"count": 63473,
"is_parallel": true,
"self": 29.81454613200458,
"children": {
"_process_rank_one_or_two_observation": {
"total": 109.46401202510333,
"count": 507784,
"is_parallel": true,
"self": 109.46401202510333
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1189.676586122054,
"count": 63474,
"self": 4.514065701028812,
"children": {
"process_trajectory": {
"total": 149.82223843902307,
"count": 63474,
"self": 149.57481680502337,
"children": {
"RLTrainer._checkpoint": {
"total": 0.24742163399969286,
"count": 2,
"self": 0.24742163399969286
}
}
},
"_update_policy": {
"total": 1035.3402819820021,
"count": 449,
"self": 426.57454671603887,
"children": {
"TorchPPOOptimizer.update": {
"total": 608.7657352659633,
"count": 22782,
"self": 608.7657352659633
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.539999155094847e-07,
"count": 1,
"self": 9.539999155094847e-07
},
"TrainerController._save_models": {
"total": 0.10643531100049586,
"count": 1,
"self": 0.0024585700002717203,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10397674100022414,
"count": 1,
"self": 0.10397674100022414
}
}
}
}
}
}
}