aalsinat's picture
First Push
e228304
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9154989123344421,
"min": 0.9154989123344421,
"max": 2.869058132171631,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8741.18359375,
"min": 8741.18359375,
"max": 29382.025390625,
"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": 12.841676712036133,
"min": 0.41906529664993286,
"max": 12.841676712036133,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2504.126953125,
"min": 81.29866790771484,
"max": 2603.97705078125,
"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": 0.06839461061891224,
"min": 0.06390483597448716,
"max": 0.0746509934026821,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27357844247564894,
"min": 0.2604732282180682,
"max": 0.3732549670134105,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21370608943934533,
"min": 0.12323143605517188,
"max": 0.2857683871452715,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8548243577573813,
"min": 0.4929257442206875,
"max": 1.4268054781006831,
"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": 24.931818181818183,
"min": 3.522727272727273,
"max": 25.563636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1097.0,
"min": 155.0,
"max": 1406.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.931818181818183,
"min": 3.522727272727273,
"max": 25.563636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1097.0,
"min": 155.0,
"max": 1406.0,
"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": "1673603067",
"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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1673603495"
},
"total": 427.67443228599996,
"count": 1,
"self": 0.3962073020001071,
"children": {
"run_training.setup": {
"total": 0.10718047899990779,
"count": 1,
"self": 0.10718047899990779
},
"TrainerController.start_learning": {
"total": 427.17104450499994,
"count": 1,
"self": 0.555752005000727,
"children": {
"TrainerController._reset_env": {
"total": 9.6670657169999,
"count": 1,
"self": 9.6670657169999
},
"TrainerController.advance": {
"total": 416.8343284249994,
"count": 18203,
"self": 0.2788614049898115,
"children": {
"env_step": {
"total": 416.5554670200096,
"count": 18203,
"self": 270.34546185801855,
"children": {
"SubprocessEnvManager._take_step": {
"total": 145.9226080239912,
"count": 18203,
"self": 1.3798579809799776,
"children": {
"TorchPolicy.evaluate": {
"total": 144.5427500430112,
"count": 18203,
"self": 33.37741491100701,
"children": {
"TorchPolicy.sample_actions": {
"total": 111.1653351320042,
"count": 18203,
"self": 111.1653351320042
}
}
}
}
},
"workers": {
"total": 0.28739713799984656,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 425.9403456369961,
"count": 18203,
"is_parallel": true,
"self": 206.1231536289995,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006212529000094946,
"count": 1,
"is_parallel": true,
"self": 0.0035915670001713806,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0026209619999235656,
"count": 10,
"is_parallel": true,
"self": 0.0026209619999235656
}
}
},
"UnityEnvironment.step": {
"total": 0.03177731900007075,
"count": 1,
"is_parallel": true,
"self": 0.0003457510000544062,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038220200008254324,
"count": 1,
"is_parallel": true,
"self": 0.00038220200008254324
},
"communicator.exchange": {
"total": 0.02924884399999428,
"count": 1,
"is_parallel": true,
"self": 0.02924884399999428
},
"steps_from_proto": {
"total": 0.0018005219999395194,
"count": 1,
"is_parallel": true,
"self": 0.000415512000245144,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013850099996943754,
"count": 10,
"is_parallel": true,
"self": 0.0013850099996943754
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 219.8171920079966,
"count": 18202,
"is_parallel": true,
"self": 8.310289541989277,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.881942325994146,
"count": 18202,
"is_parallel": true,
"self": 4.881942325994146
},
"communicator.exchange": {
"total": 177.01145309800472,
"count": 18202,
"is_parallel": true,
"self": 177.01145309800472
},
"steps_from_proto": {
"total": 29.61350704200845,
"count": 18202,
"is_parallel": true,
"self": 6.4597732820291185,
"children": {
"_process_rank_one_or_two_observation": {
"total": 23.153733759979332,
"count": 182020,
"is_parallel": true,
"self": 23.153733759979332
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.646100001082232e-05,
"count": 1,
"self": 4.646100001082232e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 413.8742800609482,
"count": 363339,
"is_parallel": true,
"self": 9.279140905977215,
"children": {
"process_trajectory": {
"total": 236.20885710996936,
"count": 363339,
"is_parallel": true,
"self": 235.50451547896944,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7043416309999202,
"count": 4,
"is_parallel": true,
"self": 0.7043416309999202
}
}
},
"_update_policy": {
"total": 168.38628204500162,
"count": 90,
"is_parallel": true,
"self": 45.01469884100311,
"children": {
"TorchPPOOptimizer.update": {
"total": 123.37158320399851,
"count": 4587,
"is_parallel": true,
"self": 123.37158320399851
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11385189699990406,
"count": 1,
"self": 0.0008289999998396524,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1130228970000644,
"count": 1,
"self": 0.1130228970000644
}
}
}
}
}
}
}