manmyung's picture
First Push
66aa304
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0019917488098145,
"min": 1.0019917488098145,
"max": 2.8590915203094482,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9589.0615234375,
"min": 9589.0615234375,
"max": 29279.95703125,
"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": 13.010966300964355,
"min": 0.28041690587997437,
"max": 13.010966300964355,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2537.138427734375,
"min": 54.40087890625,
"max": 2643.703125,
"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": 0.06947090661904634,
"min": 0.06348234082949655,
"max": 0.07565892083049916,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27788362647618536,
"min": 0.2539293633179862,
"max": 0.36903879350489555,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20349893506011704,
"min": 0.1250269747209078,
"max": 0.31859483526033516,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8139957402404682,
"min": 0.5001078988836312,
"max": 1.308419291587437,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.130097290000004e-06,
"min": 8.130097290000004e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.2520389160000015e-05,
"min": 3.2520389160000015e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10271,
"min": 0.10271,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41084,
"min": 0.41084,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00014522900000000006,
"min": 0.00014522900000000006,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005809160000000002,
"min": 0.0005809160000000002,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.772727272727273,
"min": 3.2045454545454546,
"max": 25.772727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1134.0,
"min": 141.0,
"max": 1408.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.772727272727273,
"min": 3.2045454545454546,
"max": 25.772727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1134.0,
"min": 141.0,
"max": 1408.0,
"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": "1689472097",
"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/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": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1689472588"
},
"total": 491.562002382,
"count": 1,
"self": 0.4389662870000848,
"children": {
"run_training.setup": {
"total": 0.05013476199997058,
"count": 1,
"self": 0.05013476199997058
},
"TrainerController.start_learning": {
"total": 491.07290133299995,
"count": 1,
"self": 0.5894736979979598,
"children": {
"TrainerController._reset_env": {
"total": 4.440837694000038,
"count": 1,
"self": 4.440837694000038
},
"TrainerController.advance": {
"total": 485.8974027320019,
"count": 18203,
"self": 0.29459482799637726,
"children": {
"env_step": {
"total": 485.60280790400554,
"count": 18203,
"self": 352.4101666650092,
"children": {
"SubprocessEnvManager._take_step": {
"total": 132.90094320599798,
"count": 18203,
"self": 1.9218233079985225,
"children": {
"TorchPolicy.evaluate": {
"total": 130.97911989799945,
"count": 18203,
"self": 130.97911989799945
}
}
},
"workers": {
"total": 0.2916980329983403,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 489.40724463899795,
"count": 18203,
"is_parallel": true,
"self": 229.32727094899968,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005668956000022263,
"count": 1,
"is_parallel": true,
"self": 0.004103434999933597,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015655210000886655,
"count": 10,
"is_parallel": true,
"self": 0.0015655210000886655
}
}
},
"UnityEnvironment.step": {
"total": 0.03791752099999712,
"count": 1,
"is_parallel": true,
"self": 0.0007473630000163212,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00036385999999311025,
"count": 1,
"is_parallel": true,
"self": 0.00036385999999311025
},
"communicator.exchange": {
"total": 0.03434660900001063,
"count": 1,
"is_parallel": true,
"self": 0.03434660900001063
},
"steps_from_proto": {
"total": 0.002459688999977061,
"count": 1,
"is_parallel": true,
"self": 0.0004381559999728779,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002021533000004183,
"count": 10,
"is_parallel": true,
"self": 0.002021533000004183
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 260.07997368999827,
"count": 18202,
"is_parallel": true,
"self": 11.131574253994245,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.5495555400000285,
"count": 18202,
"is_parallel": true,
"self": 5.5495555400000285
},
"communicator.exchange": {
"total": 205.65895869700745,
"count": 18202,
"is_parallel": true,
"self": 205.65895869700745
},
"steps_from_proto": {
"total": 37.73988519899655,
"count": 18202,
"is_parallel": true,
"self": 6.854318403988486,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.88556679500806,
"count": 182020,
"is_parallel": true,
"self": 30.88556679500806
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001689829999804715,
"count": 1,
"self": 0.0001689829999804715,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 482.0500981969762,
"count": 463147,
"is_parallel": true,
"self": 10.403512275954597,
"children": {
"process_trajectory": {
"total": 264.51878178202156,
"count": 463147,
"is_parallel": true,
"self": 263.7624818340217,
"children": {
"RLTrainer._checkpoint": {
"total": 0.756299947999878,
"count": 4,
"is_parallel": true,
"self": 0.756299947999878
}
}
},
"_update_policy": {
"total": 207.12780413900003,
"count": 90,
"is_parallel": true,
"self": 78.96328128499806,
"children": {
"TorchPPOOptimizer.update": {
"total": 128.16452285400197,
"count": 4587,
"is_parallel": true,
"self": 128.16452285400197
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14501822600004743,
"count": 1,
"self": 0.0009449120001363553,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14407331399991108,
"count": 1,
"self": 0.14407331399991108
}
}
}
}
}
}
}