zslrmhb's picture
First Push
bcf37ab
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.1216756105422974,
"min": 1.1216756105422974,
"max": 2.8602914810180664,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10734.435546875,
"min": 10734.435546875,
"max": 29449.560546875,
"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": 12.54658317565918,
"min": 0.4935412108898163,
"max": 12.54658317565918,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2446.583740234375,
"min": 95.74699401855469,
"max": 2499.59716796875,
"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": 0.06974159946149289,
"min": 0.0605246219162355,
"max": 0.07469160040101783,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27896639784597155,
"min": 0.259211836790771,
"max": 0.36407622401191686,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2004120465294988,
"min": 0.1266241512631121,
"max": 0.2727296624697891,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8016481861179952,
"min": 0.5064966050524484,
"max": 1.3636483123489453,
"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": 25.613636363636363,
"min": 3.6818181818181817,
"max": 25.613636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1127.0,
"min": 162.0,
"max": 1355.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.613636363636363,
"min": 3.6818181818181817,
"max": 25.613636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1127.0,
"min": 162.0,
"max": 1355.0,
"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": "1691014308",
"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": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1691014826"
},
"total": 517.686518492,
"count": 1,
"self": 0.8432660769999529,
"children": {
"run_training.setup": {
"total": 0.0668448950000311,
"count": 1,
"self": 0.0668448950000311
},
"TrainerController.start_learning": {
"total": 516.77640752,
"count": 1,
"self": 0.6246359879968395,
"children": {
"TrainerController._reset_env": {
"total": 5.822301476000007,
"count": 1,
"self": 5.822301476000007
},
"TrainerController.advance": {
"total": 510.077225062003,
"count": 18226,
"self": 0.32006407001745174,
"children": {
"env_step": {
"total": 509.75716099198553,
"count": 18226,
"self": 371.540615490969,
"children": {
"SubprocessEnvManager._take_step": {
"total": 137.89463286700845,
"count": 18226,
"self": 1.855414578014802,
"children": {
"TorchPolicy.evaluate": {
"total": 136.03921828899365,
"count": 18226,
"self": 136.03921828899365
}
}
},
"workers": {
"total": 0.321912634008072,
"count": 18226,
"self": 0.0,
"children": {
"worker_root": {
"total": 514.8053065999843,
"count": 18226,
"is_parallel": true,
"self": 242.53409322197558,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006364264000012554,
"count": 1,
"is_parallel": true,
"self": 0.004695023999829573,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001669240000182981,
"count": 10,
"is_parallel": true,
"self": 0.001669240000182981
}
}
},
"UnityEnvironment.step": {
"total": 0.03625378999993245,
"count": 1,
"is_parallel": true,
"self": 0.0006653489998598161,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00034758499998588377,
"count": 1,
"is_parallel": true,
"self": 0.00034758499998588377
},
"communicator.exchange": {
"total": 0.03279044500004602,
"count": 1,
"is_parallel": true,
"self": 0.03279044500004602
},
"steps_from_proto": {
"total": 0.002450411000040731,
"count": 1,
"is_parallel": true,
"self": 0.0005339209998282968,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001916490000212434,
"count": 10,
"is_parallel": true,
"self": 0.001916490000212434
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 272.2712133780087,
"count": 18225,
"is_parallel": true,
"self": 11.35696129597261,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.744128431011859,
"count": 18225,
"is_parallel": true,
"self": 5.744128431011859
},
"communicator.exchange": {
"total": 215.5855656960042,
"count": 18225,
"is_parallel": true,
"self": 215.5855656960042
},
"steps_from_proto": {
"total": 39.584557955020045,
"count": 18225,
"is_parallel": true,
"self": 7.365436550066647,
"children": {
"_process_rank_one_or_two_observation": {
"total": 32.2191214049534,
"count": 182250,
"is_parallel": true,
"self": 32.2191214049534
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014076200000090466,
"count": 1,
"self": 0.00014076200000090466,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 505.94316528900924,
"count": 473609,
"is_parallel": true,
"self": 11.429343931005747,
"children": {
"process_trajectory": {
"total": 276.63620626100396,
"count": 473609,
"is_parallel": true,
"self": 274.1546450440039,
"children": {
"RLTrainer._checkpoint": {
"total": 2.481561217000035,
"count": 4,
"is_parallel": true,
"self": 2.481561217000035
}
}
},
"_update_policy": {
"total": 217.87761509699953,
"count": 90,
"is_parallel": true,
"self": 86.36353213498728,
"children": {
"TorchPPOOptimizer.update": {
"total": 131.51408296201225,
"count": 4587,
"is_parallel": true,
"self": 131.51408296201225
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.2521042320001925,
"count": 1,
"self": 0.001222868000240851,
"children": {
"RLTrainer._checkpoint": {
"total": 0.25088136399995165,
"count": 1,
"self": 0.25088136399995165
}
}
}
}
}
}
}