ahaedike's picture
First Push
504f70f
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9979687333106995,
"min": 0.9979687333106995,
"max": 2.8658034801483154,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9550.560546875,
"min": 9550.560546875,
"max": 29506.3125,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.5727698802948,
"min": 0.26750555634498596,
"max": 2.6008527278900146,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 501.69012451171875,
"min": 51.896080017089844,
"max": 530.573974609375,
"count": 20
},
"SnowballTarget.Policy.CuriosityValueEstimate.mean": {
"value": 0.004046767950057983,
"min": 0.0012680103536695242,
"max": 0.006228377111256123,
"count": 20
},
"SnowballTarget.Policy.CuriosityValueEstimate.sum": {
"value": 0.7891197800636292,
"min": 0.25867411494255066,
"max": 1.2768173217773438,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06826267521904025,
"min": 0.0645155973069111,
"max": 0.07598544383152186,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.273050700876161,
"min": 0.2580623892276444,
"max": 0.37992721915760935,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.06880414310623618,
"min": 0.03271402967020906,
"max": 0.07982423875992205,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.27521657242494474,
"min": 0.13085611868083624,
"max": 0.3932376244634974,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Losses.CuriosityForwardLoss.mean": {
"value": 0.039687921804394205,
"min": 0.03878352112483745,
"max": 0.12515270445203663,
"count": 20
},
"SnowballTarget.Losses.CuriosityForwardLoss.sum": {
"value": 0.15875168721757682,
"min": 0.15875168721757682,
"max": 0.5006108178081465,
"count": 20
},
"SnowballTarget.Losses.CuriosityInverseLoss.mean": {
"value": 0.8903774952187258,
"min": 0.8903774952187258,
"max": 2.78806949209641,
"count": 20
},
"SnowballTarget.Losses.CuriosityInverseLoss.sum": {
"value": 3.561509980874903,
"min": 3.561509980874903,
"max": 13.051959182701857,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.386363636363637,
"min": 3.2045454545454546,
"max": 25.568181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1117.0,
"min": 141.0,
"max": 1393.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.386363636363637,
"min": 3.2045454545454546,
"max": 25.568181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1117.0,
"min": 141.0,
"max": 1393.0,
"count": 20
},
"SnowballTarget.Policy.CuriosityReward.mean": {
"value": 0.08181738935739057,
"min": 0.07844753952866251,
"max": 0.13470784202641384,
"count": 20
},
"SnowballTarget.Policy.CuriosityReward.sum": {
"value": 3.5999651317251846,
"min": 3.5999651317251846,
"max": 7.408931311452761,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1696630345",
"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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.0.1+cu118",
"numpy_version": "1.21.2",
"end_time_seconds": "1696630913"
},
"total": 567.969684439,
"count": 1,
"self": 0.42575900999986516,
"children": {
"run_training.setup": {
"total": 0.05038279500001863,
"count": 1,
"self": 0.05038279500001863
},
"TrainerController.start_learning": {
"total": 567.4935426340002,
"count": 1,
"self": 0.6150138349775034,
"children": {
"TrainerController._reset_env": {
"total": 7.198656584999981,
"count": 1,
"self": 7.198656584999981
},
"TrainerController.advance": {
"total": 559.5824567690224,
"count": 18202,
"self": 0.28601455701141276,
"children": {
"env_step": {
"total": 559.296442212011,
"count": 18202,
"self": 415.81972813100276,
"children": {
"SubprocessEnvManager._take_step": {
"total": 143.17141161299662,
"count": 18202,
"self": 1.5457510910159726,
"children": {
"TorchPolicy.evaluate": {
"total": 141.62566052198065,
"count": 18202,
"self": 141.62566052198065
}
}
},
"workers": {
"total": 0.3053024680116323,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 566.0994766879982,
"count": 18202,
"is_parallel": true,
"self": 315.51120017800145,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0021619990000090183,
"count": 1,
"is_parallel": true,
"self": 0.0005966780000790095,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015653209999300088,
"count": 10,
"is_parallel": true,
"self": 0.0015653209999300088
}
}
},
"UnityEnvironment.step": {
"total": 0.08490858599998319,
"count": 1,
"is_parallel": true,
"self": 0.0006361690000176168,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00045589199999085395,
"count": 1,
"is_parallel": true,
"self": 0.00045589199999085395
},
"communicator.exchange": {
"total": 0.08154679599999781,
"count": 1,
"is_parallel": true,
"self": 0.08154679599999781
},
"steps_from_proto": {
"total": 0.0022697289999769055,
"count": 1,
"is_parallel": true,
"self": 0.00037782699996569136,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018919020000112141,
"count": 10,
"is_parallel": true,
"self": 0.0018919020000112141
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 250.58827650999672,
"count": 18201,
"is_parallel": true,
"self": 10.902980159005551,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.520638345996076,
"count": 18201,
"is_parallel": true,
"self": 5.520638345996076
},
"communicator.exchange": {
"total": 194.68484920799222,
"count": 18201,
"is_parallel": true,
"self": 194.68484920799222
},
"steps_from_proto": {
"total": 39.479808797002875,
"count": 18201,
"is_parallel": true,
"self": 7.430284393999955,
"children": {
"_process_rank_one_or_two_observation": {
"total": 32.04952440300292,
"count": 182010,
"is_parallel": true,
"self": 32.04952440300292
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001813440001114941,
"count": 1,
"self": 0.0001813440001114941,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 556.0280860110071,
"count": 459330,
"is_parallel": true,
"self": 9.873806304101663,
"children": {
"process_trajectory": {
"total": 286.22299736390676,
"count": 459330,
"is_parallel": true,
"self": 285.6179423029066,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6050550610001437,
"count": 4,
"is_parallel": true,
"self": 0.6050550610001437
}
}
},
"_update_policy": {
"total": 259.93128234299866,
"count": 90,
"is_parallel": true,
"self": 164.9237762519905,
"children": {
"TorchPPOOptimizer.update": {
"total": 95.00750609100817,
"count": 4587,
"is_parallel": true,
"self": 95.00750609100817
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09723410100014007,
"count": 1,
"self": 0.0008330190000833682,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0964010820000567,
"count": 1,
"self": 0.0964010820000567
}
}
}
}
}
}
}