FBM's picture
first update
01e6d92
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.1363229900598526,
"min": 0.12427036464214325,
"max": 1.453099250793457,
"count": 100
},
"Pyramids.Policy.Entropy.sum": {
"value": 4083.14599609375,
"min": 3746.005859375,
"max": 44081.21875,
"count": 100
},
"Pyramids.Step.mean": {
"value": 2999973.0,
"min": 29973.0,
"max": 2999973.0,
"count": 100
},
"Pyramids.Step.sum": {
"value": 2999973.0,
"min": 29973.0,
"max": 2999973.0,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.7780754566192627,
"min": -0.16031672060489655,
"max": 0.830024003982544,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 233.42263793945312,
"min": -38.636329650878906,
"max": 257.30743408203125,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.00016749586211517453,
"min": -0.013276143930852413,
"max": 0.48031529784202576,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 0.050248757004737854,
"min": -3.969567060470581,
"max": 114.3150405883789,
"count": 100
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06789399252045855,
"min": 0.06447975217140214,
"max": 0.07358201840718191,
"count": 100
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9505158952864197,
"min": 0.5751587309526811,
"max": 1.1037302761077288,
"count": 100
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015169094938928974,
"min": 0.0007364418043245387,
"max": 0.017416204440191256,
"count": 100
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.21236732914500564,
"min": 0.008100859847569926,
"max": 0.24559065859648402,
"count": 100
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.5436994854666695e-06,
"min": 1.5436994854666695e-06,
"max": 0.00029828401307199586,
"count": 100
},
"Pyramids.Policy.LearningRate.sum": {
"value": 2.161179279653337e-05,
"min": 2.161179279653337e-05,
"max": 0.0038843723052092664,
"count": 100
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10051453333333331,
"min": 0.10051453333333331,
"max": 0.1994280041666667,
"count": 100
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4072034666666664,
"min": 1.4072034666666664,
"max": 2.782497,
"count": 100
},
"Pyramids.Policy.Beta.mean": {
"value": 6.140188000000009e-05,
"min": 6.140188000000009e-05,
"max": 0.00994285761625,
"count": 100
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0008596263200000014,
"min": 0.0008596263200000014,
"max": 0.12948959426,
"count": 100
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.008998597972095013,
"min": 0.008516975678503513,
"max": 0.6815822124481201,
"count": 100
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.12598037719726562,
"min": 0.11923766136169434,
"max": 5.452657699584961,
"count": 100
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 217.42105263157896,
"min": 217.42105263157896,
"max": 999.0,
"count": 100
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28917.0,
"min": 16388.0,
"max": 32846.0,
"count": 100
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7680736703980238,
"min": -0.999987552408129,
"max": 1.780555541758184,
"count": 100
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 235.15379816293716,
"min": -31.999601677060127,
"max": 241.33759778738022,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7680736703980238,
"min": -0.999987552408129,
"max": 1.780555541758184,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 235.15379816293716,
"min": -31.999601677060127,
"max": 241.33759778738022,
"count": 100
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.0205993578651976,
"min": 0.0205993578651976,
"max": 13.334137524752055,
"count": 100
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.7397145960712805,
"min": 2.6367782971065026,
"max": 226.68033792078495,
"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": "1673854787",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training1 --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1673861601"
},
"total": 6813.930465126,
"count": 1,
"self": 0.4764324299994769,
"children": {
"run_training.setup": {
"total": 0.10995766500002446,
"count": 1,
"self": 0.10995766500002446
},
"TrainerController.start_learning": {
"total": 6813.344075031,
"count": 1,
"self": 3.9118559786174956,
"children": {
"TrainerController._reset_env": {
"total": 9.55991955799999,
"count": 1,
"self": 9.55991955799999
},
"TrainerController.advance": {
"total": 6799.779894765383,
"count": 195338,
"self": 3.9590551252485966,
"children": {
"env_step": {
"total": 4792.916172006062,
"count": 195338,
"self": 4483.058090124122,
"children": {
"SubprocessEnvManager._take_step": {
"total": 307.47538874599707,
"count": 195338,
"self": 12.621261848955498,
"children": {
"TorchPolicy.evaluate": {
"total": 294.85412689704157,
"count": 187572,
"self": 100.02000689787963,
"children": {
"TorchPolicy.sample_actions": {
"total": 194.83411999916194,
"count": 187572,
"self": 194.83411999916194
}
}
}
}
},
"workers": {
"total": 2.3826931359426453,
"count": 195338,
"self": 0.0,
"children": {
"worker_root": {
"total": 6799.650391418936,
"count": 195338,
"is_parallel": true,
"self": 2612.394822277887,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006139565000012226,
"count": 1,
"is_parallel": true,
"self": 0.003937789000076464,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022017759999357622,
"count": 8,
"is_parallel": true,
"self": 0.0022017759999357622
}
}
},
"UnityEnvironment.step": {
"total": 0.048357059000011304,
"count": 1,
"is_parallel": true,
"self": 0.0004950440000470735,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004573439999830953,
"count": 1,
"is_parallel": true,
"self": 0.0004573439999830953
},
"communicator.exchange": {
"total": 0.04582161399997631,
"count": 1,
"is_parallel": true,
"self": 0.04582161399997631
},
"steps_from_proto": {
"total": 0.0015830570000048283,
"count": 1,
"is_parallel": true,
"self": 0.00042210599997360987,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011609510000312184,
"count": 8,
"is_parallel": true,
"self": 0.0011609510000312184
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 4187.255569141049,
"count": 195337,
"is_parallel": true,
"self": 84.93207818175142,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 67.18929023802565,
"count": 195337,
"is_parallel": true,
"self": 67.18929023802565
},
"communicator.exchange": {
"total": 3731.126960826181,
"count": 195337,
"is_parallel": true,
"self": 3731.126960826181
},
"steps_from_proto": {
"total": 304.0072398950908,
"count": 195337,
"is_parallel": true,
"self": 65.95801152710396,
"children": {
"_process_rank_one_or_two_observation": {
"total": 238.0492283679868,
"count": 1562696,
"is_parallel": true,
"self": 238.0492283679868
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 2002.904667634072,
"count": 195338,
"self": 7.4847126988950095,
"children": {
"process_trajectory": {
"total": 440.7632468611862,
"count": 195338,
"self": 440.20546875218565,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5577781090005374,
"count": 6,
"self": 0.5577781090005374
}
}
},
"_update_policy": {
"total": 1554.6567080739908,
"count": 1400,
"self": 601.822193827021,
"children": {
"TorchPPOOptimizer.update": {
"total": 952.8345142469698,
"count": 68352,
"self": 952.8345142469698
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0130006558028981e-06,
"count": 1,
"self": 1.0130006558028981e-06
},
"TrainerController._save_models": {
"total": 0.09240371599935315,
"count": 1,
"self": 0.0013888479988963809,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09101486800045677,
"count": 1,
"self": 0.09101486800045677
}
}
}
}
}
}
}