adutchscotsman's picture
First Push
24addf9
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5790771245956421,
"min": 0.5460456609725952,
"max": 1.4837881326675415,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 17196.2734375,
"min": 16617.26171875,
"max": 45012.1953125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989889.0,
"min": 29902.0,
"max": 989889.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989889.0,
"min": 29902.0,
"max": 989889.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.18456396460533142,
"min": -0.09519436955451965,
"max": 0.19893212616443634,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 46.32555389404297,
"min": -22.846649169921875,
"max": 50.727691650390625,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.29602763056755066,
"min": -0.017827358096837997,
"max": 0.34487876296043396,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 74.30293273925781,
"min": -4.545976161956787,
"max": 81.73626708984375,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07008602623301115,
"min": 0.06463045386287074,
"max": 0.07240585912022643,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.981204367262156,
"min": 0.5043134090712096,
"max": 1.0231486340321592,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.03730504111237159,
"min": 0.00013656261948400363,
"max": 0.03730504111237159,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.5222705755732022,
"min": 0.0016387514338080437,
"max": 0.5222705755732022,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.585833185707144e-06,
"min": 7.585833185707144e-06,
"max": 0.00029523505873117143,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010620166459990001,
"min": 0.00010620166459990001,
"max": 0.0033822233725923,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10252857857142858,
"min": 0.10252857857142858,
"max": 0.19841168571428572,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4354001,
"min": 1.3888818,
"max": 2.5274077000000004,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002626049992857143,
"min": 0.0002626049992857143,
"max": 0.009841327402857142,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036764699900000003,
"min": 0.0036764699900000003,
"max": 0.11276802923000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.012705421075224876,
"min": 0.012705421075224876,
"max": 0.4501160681247711,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.17787589132785797,
"min": 0.17787589132785797,
"max": 3.1508123874664307,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 676.5348837209302,
"min": 620.625,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29091.0,
"min": 16701.0,
"max": 33082.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.7186139212098233,
"min": -0.9999750521965325,
"max": 0.8408652673266372,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 30.9003986120224,
"min": -31.99920167028904,
"max": 41.20239809900522,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.7186139212098233,
"min": -0.9999750521965325,
"max": 0.8408652673266372,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 30.9003986120224,
"min": -31.99920167028904,
"max": 41.20239809900522,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.08839131033773599,
"min": 0.0851667387926552,
"max": 8.483155116438866,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.8008263445226476,
"min": 3.8008263445226476,
"max": 144.21363697946072,
"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": "1700829735",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1700831901"
},
"total": 2166.9000152040003,
"count": 1,
"self": 0.4767642159999923,
"children": {
"run_training.setup": {
"total": 0.06226442700017287,
"count": 1,
"self": 0.06226442700017287
},
"TrainerController.start_learning": {
"total": 2166.360986561,
"count": 1,
"self": 1.3725219229031609,
"children": {
"TrainerController._reset_env": {
"total": 5.033508770000026,
"count": 1,
"self": 5.033508770000026
},
"TrainerController.advance": {
"total": 2159.880578041097,
"count": 63263,
"self": 1.4989307491105137,
"children": {
"env_step": {
"total": 1515.3621111159932,
"count": 63263,
"self": 1381.5920559139786,
"children": {
"SubprocessEnvManager._take_step": {
"total": 132.91053991303716,
"count": 63263,
"self": 4.70214460709667,
"children": {
"TorchPolicy.evaluate": {
"total": 128.20839530594048,
"count": 62562,
"self": 128.20839530594048
}
}
},
"workers": {
"total": 0.8595152889774909,
"count": 63263,
"self": 0.0,
"children": {
"worker_root": {
"total": 2161.7624180109606,
"count": 63263,
"is_parallel": true,
"self": 898.9705250040151,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0029475050000655756,
"count": 1,
"is_parallel": true,
"self": 0.000796342999819899,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021511620002456766,
"count": 8,
"is_parallel": true,
"self": 0.0021511620002456766
}
}
},
"UnityEnvironment.step": {
"total": 0.04763833000015438,
"count": 1,
"is_parallel": true,
"self": 0.0005701320001207932,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005324570001903339,
"count": 1,
"is_parallel": true,
"self": 0.0005324570001903339
},
"communicator.exchange": {
"total": 0.044864776999929745,
"count": 1,
"is_parallel": true,
"self": 0.044864776999929745
},
"steps_from_proto": {
"total": 0.0016709639999135106,
"count": 1,
"is_parallel": true,
"self": 0.0003838790012196114,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012870849986938993,
"count": 8,
"is_parallel": true,
"self": 0.0012870849986938993
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1262.7918930069454,
"count": 63262,
"is_parallel": true,
"self": 34.155355731905274,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.218638860045303,
"count": 63262,
"is_parallel": true,
"self": 24.218638860045303
},
"communicator.exchange": {
"total": 1107.5767764639413,
"count": 63262,
"is_parallel": true,
"self": 1107.5767764639413
},
"steps_from_proto": {
"total": 96.84112195105354,
"count": 63262,
"is_parallel": true,
"self": 19.45692200300209,
"children": {
"_process_rank_one_or_two_observation": {
"total": 77.38419994805145,
"count": 506096,
"is_parallel": true,
"self": 77.38419994805145
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 643.0195361759934,
"count": 63263,
"self": 2.5519632150012512,
"children": {
"process_trajectory": {
"total": 125.12820541598694,
"count": 63263,
"self": 124.96889238898575,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15931302700118977,
"count": 2,
"self": 0.15931302700118977
}
}
},
"_update_policy": {
"total": 515.3393675450052,
"count": 446,
"self": 310.4269578010426,
"children": {
"TorchPPOOptimizer.update": {
"total": 204.9124097439626,
"count": 22758,
"self": 204.9124097439626
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.669993232819252e-07,
"count": 1,
"self": 9.669993232819252e-07
},
"TrainerController._save_models": {
"total": 0.07437686000048416,
"count": 1,
"self": 0.001315127000452776,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07306173300003138,
"count": 1,
"self": 0.07306173300003138
}
}
}
}
}
}
}