giovannidispoto's picture
First Push
78b7831
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9788471460342407,
"min": 0.9788471460342407,
"max": 2.8679587841033936,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9389.1015625,
"min": 9389.1015625,
"max": 29402.314453125,
"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": 12.504998207092285,
"min": 0.37799009680747986,
"max": 12.504998207092285,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2438.474609375,
"min": 73.330078125,
"max": 2534.27001953125,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06476969772683885,
"min": 0.06314935375749152,
"max": 0.07632913691700464,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2590787909073554,
"min": 0.2525974150299661,
"max": 0.37021629803173967,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21304371434391714,
"min": 0.1307990687954075,
"max": 0.28081115073360063,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8521748573756686,
"min": 0.52319627518163,
"max": 1.4040557536680032,
"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": 24.40909090909091,
"min": 3.7954545454545454,
"max": 25.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1074.0,
"min": 167.0,
"max": 1335.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.40909090909091,
"min": 3.7954545454545454,
"max": 25.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1074.0,
"min": 167.0,
"max": 1335.0,
"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": "1689867356",
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
"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": "1689867847"
},
"total": 490.9571220109999,
"count": 1,
"self": 0.7841313919996082,
"children": {
"run_training.setup": {
"total": 0.03932012600012058,
"count": 1,
"self": 0.03932012600012058
},
"TrainerController.start_learning": {
"total": 490.1336704930002,
"count": 1,
"self": 0.5899364249933114,
"children": {
"TrainerController._reset_env": {
"total": 5.830718632000071,
"count": 1,
"self": 5.830718632000071
},
"TrainerController.advance": {
"total": 483.47448379900675,
"count": 18216,
"self": 0.2816884379997191,
"children": {
"env_step": {
"total": 483.19279536100703,
"count": 18216,
"self": 351.2525334239856,
"children": {
"SubprocessEnvManager._take_step": {
"total": 131.6448131420027,
"count": 18216,
"self": 1.732878282024103,
"children": {
"TorchPolicy.evaluate": {
"total": 129.9119348599786,
"count": 18216,
"self": 129.9119348599786
}
}
},
"workers": {
"total": 0.29544879501872856,
"count": 18216,
"self": 0.0,
"children": {
"worker_root": {
"total": 488.4132275659906,
"count": 18216,
"is_parallel": true,
"self": 227.9973050789995,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005958715000133452,
"count": 1,
"is_parallel": true,
"self": 0.004405325000334415,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015533899997990375,
"count": 10,
"is_parallel": true,
"self": 0.0015533899997990375
}
}
},
"UnityEnvironment.step": {
"total": 0.07006698899999719,
"count": 1,
"is_parallel": true,
"self": 0.0006888759999128524,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004240109999500419,
"count": 1,
"is_parallel": true,
"self": 0.0004240109999500419
},
"communicator.exchange": {
"total": 0.06681861800007027,
"count": 1,
"is_parallel": true,
"self": 0.06681861800007027
},
"steps_from_proto": {
"total": 0.002135484000064025,
"count": 1,
"is_parallel": true,
"self": 0.00036091799984205863,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017745660002219665,
"count": 10,
"is_parallel": true,
"self": 0.0017745660002219665
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 260.4159224869911,
"count": 18215,
"is_parallel": true,
"self": 11.131777239980238,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.416908354022098,
"count": 18215,
"is_parallel": true,
"self": 5.416908354022098
},
"communicator.exchange": {
"total": 207.30681064199484,
"count": 18215,
"is_parallel": true,
"self": 207.30681064199484
},
"steps_from_proto": {
"total": 36.56042625099394,
"count": 18215,
"is_parallel": true,
"self": 6.804020765974428,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.756405485019513,
"count": 182150,
"is_parallel": true,
"self": 29.756405485019513
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00017850200015345763,
"count": 1,
"self": 0.00017850200015345763,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 479.4233521000058,
"count": 452114,
"is_parallel": true,
"self": 10.528652974964416,
"children": {
"process_trajectory": {
"total": 263.21561376804175,
"count": 452114,
"is_parallel": true,
"self": 261.52927228204135,
"children": {
"RLTrainer._checkpoint": {
"total": 1.6863414860004013,
"count": 4,
"is_parallel": true,
"self": 1.6863414860004013
}
}
},
"_update_policy": {
"total": 205.67908535699962,
"count": 90,
"is_parallel": true,
"self": 80.80144419899534,
"children": {
"TorchPPOOptimizer.update": {
"total": 124.87764115800428,
"count": 4584,
"is_parallel": true,
"self": 124.87764115800428
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.23835313499989752,
"count": 1,
"self": 0.001148451000062778,
"children": {
"RLTrainer._checkpoint": {
"total": 0.23720468399983474,
"count": 1,
"self": 0.23720468399983474
}
}
}
}
}
}
}