cagarraz's picture
First Push
36f26e2
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.112331748008728,
"min": 1.112331748008728,
"max": 2.857112169265747,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10657.25,
"min": 10657.25,
"max": 29291.11328125,
"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": 12.582632064819336,
"min": 0.3530924320220947,
"max": 12.582632064819336,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2453.61328125,
"min": 68.49993133544922,
"max": 2530.25927734375,
"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": 0.06679824586136224,
"min": 0.0546428676731796,
"max": 0.07521982329587142,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26719298344544895,
"min": 0.2185714706927184,
"max": 0.37609911647935707,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19587859606333807,
"min": 0.11932700955281582,
"max": 0.2672095281236312,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7835143842533523,
"min": 0.4773080382112633,
"max": 1.3129300632897545,
"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.Environment.CumulativeReward.mean": {
"value": 24.727272727272727,
"min": 3.3181818181818183,
"max": 24.863636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1088.0,
"min": 146.0,
"max": 1364.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.727272727272727,
"min": 3.3181818181818183,
"max": 24.863636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1088.0,
"min": 146.0,
"max": 1364.0,
"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": "1688890011",
"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": "1688890480"
},
"total": 468.93000337599995,
"count": 1,
"self": 0.7875347289998444,
"children": {
"run_training.setup": {
"total": 0.0492438180000363,
"count": 1,
"self": 0.0492438180000363
},
"TrainerController.start_learning": {
"total": 468.09322482900006,
"count": 1,
"self": 0.5591786809882251,
"children": {
"TrainerController._reset_env": {
"total": 5.271288996999942,
"count": 1,
"self": 5.271288996999942
},
"TrainerController.advance": {
"total": 462.037254623012,
"count": 18217,
"self": 0.28678263401366166,
"children": {
"env_step": {
"total": 461.75047198899836,
"count": 18217,
"self": 337.9291180689926,
"children": {
"SubprocessEnvManager._take_step": {
"total": 123.56135204500993,
"count": 18217,
"self": 1.8608553400081291,
"children": {
"TorchPolicy.evaluate": {
"total": 121.7004967050018,
"count": 18217,
"self": 121.7004967050018
}
}
},
"workers": {
"total": 0.2600018749958508,
"count": 18217,
"self": 0.0,
"children": {
"worker_root": {
"total": 466.44791657099654,
"count": 18217,
"is_parallel": true,
"self": 220.72775647899277,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.012265931999991153,
"count": 1,
"is_parallel": true,
"self": 0.010668298000155119,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015976339998360345,
"count": 10,
"is_parallel": true,
"self": 0.0015976339998360345
}
}
},
"UnityEnvironment.step": {
"total": 0.06667567800002416,
"count": 1,
"is_parallel": true,
"self": 0.0005843500001674329,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00043001999995340157,
"count": 1,
"is_parallel": true,
"self": 0.00043001999995340157
},
"communicator.exchange": {
"total": 0.06352661799996895,
"count": 1,
"is_parallel": true,
"self": 0.06352661799996895
},
"steps_from_proto": {
"total": 0.0021346899999343805,
"count": 1,
"is_parallel": true,
"self": 0.000491015999841693,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016436740000926875,
"count": 10,
"is_parallel": true,
"self": 0.0016436740000926875
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 245.72016009200377,
"count": 18216,
"is_parallel": true,
"self": 10.225612004016853,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.152153276002878,
"count": 18216,
"is_parallel": true,
"self": 5.152153276002878
},
"communicator.exchange": {
"total": 195.016538344992,
"count": 18216,
"is_parallel": true,
"self": 195.016538344992
},
"steps_from_proto": {
"total": 35.325856466992036,
"count": 18216,
"is_parallel": true,
"self": 6.238633442980699,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.087223024011337,
"count": 182160,
"is_parallel": true,
"self": 29.087223024011337
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001330519999100943,
"count": 1,
"self": 0.0001330519999100943,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 458.43964294601653,
"count": 433232,
"is_parallel": true,
"self": 9.645062212009975,
"children": {
"process_trajectory": {
"total": 248.87558129500667,
"count": 433232,
"is_parallel": true,
"self": 247.47898875600663,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3965925390000393,
"count": 4,
"is_parallel": true,
"self": 1.3965925390000393
}
}
},
"_update_policy": {
"total": 199.9189994389999,
"count": 90,
"is_parallel": true,
"self": 79.21720079000522,
"children": {
"TorchPPOOptimizer.update": {
"total": 120.70179864899467,
"count": 4587,
"is_parallel": true,
"self": 120.70179864899467
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.22536947599996893,
"count": 1,
"self": 0.001097780000009152,
"children": {
"RLTrainer._checkpoint": {
"total": 0.22427169599995977,
"count": 1,
"self": 0.22427169599995977
}
}
}
}
}
}
}