sanak
First Push
2821795
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7799046039581299,
"min": 0.7799046039581299,
"max": 2.871917724609375,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7437.9501953125,
"min": 7437.9501953125,
"max": 29537.673828125,
"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": 12.730555534362793,
"min": 0.4143564999103546,
"max": 12.827383041381836,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2482.458251953125,
"min": 80.38516235351562,
"max": 2616.7861328125,
"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": 0.06589969556722174,
"min": 0.06120110262551916,
"max": 0.07571420898498485,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26359878226888694,
"min": 0.24480441050207663,
"max": 0.37537728074262394,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20919377992258353,
"min": 0.11719009371054377,
"max": 0.2593799447312074,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8367751196903341,
"min": 0.4687603748421751,
"max": 1.2968997236560371,
"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": 24.636363636363637,
"min": 3.4545454545454546,
"max": 25.69090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1084.0,
"min": 152.0,
"max": 1413.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.636363636363637,
"min": 3.4545454545454546,
"max": 25.69090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1084.0,
"min": 152.0,
"max": 1413.0,
"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": "1679534934",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1679535393"
},
"total": 459.271432647,
"count": 1,
"self": 0.38512969700013855,
"children": {
"run_training.setup": {
"total": 0.10901340599991727,
"count": 1,
"self": 0.10901340599991727
},
"TrainerController.start_learning": {
"total": 458.7772895439999,
"count": 1,
"self": 0.5237417000010964,
"children": {
"TrainerController._reset_env": {
"total": 9.856087246000016,
"count": 1,
"self": 9.856087246000016
},
"TrainerController.advance": {
"total": 448.2608731599987,
"count": 18200,
"self": 0.2802081379976471,
"children": {
"env_step": {
"total": 447.98066502200106,
"count": 18200,
"self": 323.9813672740155,
"children": {
"SubprocessEnvManager._take_step": {
"total": 123.74430577399448,
"count": 18200,
"self": 2.7717863369945235,
"children": {
"TorchPolicy.evaluate": {
"total": 120.97251943699996,
"count": 18200,
"self": 120.97251943699996
}
}
},
"workers": {
"total": 0.254991973991082,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 457.3638690420005,
"count": 18200,
"is_parallel": true,
"self": 220.49604561499484,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00616938799998934,
"count": 1,
"is_parallel": true,
"self": 0.004810286000065389,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013591019999239506,
"count": 10,
"is_parallel": true,
"self": 0.0013591019999239506
}
}
},
"UnityEnvironment.step": {
"total": 0.044229983000036555,
"count": 1,
"is_parallel": true,
"self": 0.0005502720000549743,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00029303899998467386,
"count": 1,
"is_parallel": true,
"self": 0.00029303899998467386
},
"communicator.exchange": {
"total": 0.04158226399999876,
"count": 1,
"is_parallel": true,
"self": 0.04158226399999876
},
"steps_from_proto": {
"total": 0.0018044079999981477,
"count": 1,
"is_parallel": true,
"self": 0.00035138299995196576,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001453025000046182,
"count": 10,
"is_parallel": true,
"self": 0.001453025000046182
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 236.86782342700565,
"count": 18199,
"is_parallel": true,
"self": 9.335990915008892,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.036613598004806,
"count": 18199,
"is_parallel": true,
"self": 5.036613598004806
},
"communicator.exchange": {
"total": 192.4248327189904,
"count": 18199,
"is_parallel": true,
"self": 192.4248327189904
},
"steps_from_proto": {
"total": 30.07038619500156,
"count": 18199,
"is_parallel": true,
"self": 5.908334438028874,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.162051756972687,
"count": 181990,
"is_parallel": true,
"self": 24.162051756972687
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012770600005751476,
"count": 1,
"self": 0.00012770600005751476,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 445.1326131639794,
"count": 388767,
"is_parallel": true,
"self": 9.176527400016539,
"children": {
"process_trajectory": {
"total": 244.01404183596264,
"count": 388767,
"is_parallel": true,
"self": 242.97592196096275,
"children": {
"RLTrainer._checkpoint": {
"total": 1.038119874999893,
"count": 4,
"is_parallel": true,
"self": 1.038119874999893
}
}
},
"_update_policy": {
"total": 191.9420439280002,
"count": 90,
"is_parallel": true,
"self": 71.9768964520066,
"children": {
"TorchPPOOptimizer.update": {
"total": 119.9651474759936,
"count": 4584,
"is_parallel": true,
"self": 119.9651474759936
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13645973200004846,
"count": 1,
"self": 0.0009171950000563811,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13554253699999208,
"count": 1,
"self": 0.13554253699999208
}
}
}
}
}
}
}