ankandrew's picture
First train
91fa96e
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0112881660461426,
"min": 1.0112881660461426,
"max": 2.86944317817688,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9678.02734375,
"min": 9678.02734375,
"max": 29417.53125,
"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": 6.332076549530029,
"min": 0.32373034954071045,
"max": 6.332076549530029,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1234.7548828125,
"min": 62.803688049316406,
"max": 1284.0810546875,
"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": 0.06882907876370511,
"min": 0.06156901074891542,
"max": 0.07514698467532392,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27531631505482046,
"min": 0.2462760429956617,
"max": 0.3605160272947579,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.16053571636039837,
"min": 0.09353080478852945,
"max": 0.22943720186457917,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6421428654415935,
"min": 0.3741232191541178,
"max": 1.1471860093228958,
"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": 25.272727272727273,
"min": 3.1136363636363638,
"max": 25.272727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1112.0,
"min": 137.0,
"max": 1384.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.272727272727273,
"min": 3.1136363636363638,
"max": 25.272727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1112.0,
"min": 137.0,
"max": 1384.0,
"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": "1679576008",
"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": "1679576462"
},
"total": 454.3716167329999,
"count": 1,
"self": 0.6451750819999233,
"children": {
"run_training.setup": {
"total": 0.10663839099993311,
"count": 1,
"self": 0.10663839099993311
},
"TrainerController.start_learning": {
"total": 453.61980326,
"count": 1,
"self": 0.5092424310112165,
"children": {
"TrainerController._reset_env": {
"total": 9.469141282999999,
"count": 1,
"self": 9.469141282999999
},
"TrainerController.advance": {
"total": 443.3960374539888,
"count": 18206,
"self": 0.27198917097530284,
"children": {
"env_step": {
"total": 443.1240482830135,
"count": 18206,
"self": 319.69275737099974,
"children": {
"SubprocessEnvManager._take_step": {
"total": 123.16701389000718,
"count": 18206,
"self": 2.2844740770085536,
"children": {
"TorchPolicy.evaluate": {
"total": 120.88253981299863,
"count": 18206,
"self": 120.88253981299863
}
}
},
"workers": {
"total": 0.2642770220065813,
"count": 18206,
"self": 0.0,
"children": {
"worker_root": {
"total": 452.11447225898655,
"count": 18206,
"is_parallel": true,
"self": 216.94983573497848,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005590308999899207,
"count": 1,
"is_parallel": true,
"self": 0.004045162999773311,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015451460001258965,
"count": 10,
"is_parallel": true,
"self": 0.0015451460001258965
}
}
},
"UnityEnvironment.step": {
"total": 0.03494038299982094,
"count": 1,
"is_parallel": true,
"self": 0.0005877300000065588,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00033141099993372336,
"count": 1,
"is_parallel": true,
"self": 0.00033141099993372336
},
"communicator.exchange": {
"total": 0.03214789899993775,
"count": 1,
"is_parallel": true,
"self": 0.03214789899993775
},
"steps_from_proto": {
"total": 0.0018733429999429063,
"count": 1,
"is_parallel": true,
"self": 0.00037190899979577807,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015014340001471282,
"count": 10,
"is_parallel": true,
"self": 0.0015014340001471282
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 235.16463652400807,
"count": 18205,
"is_parallel": true,
"self": 9.45293221904285,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.042732831978583,
"count": 18205,
"is_parallel": true,
"self": 5.042732831978583
},
"communicator.exchange": {
"total": 190.54675091198806,
"count": 18205,
"is_parallel": true,
"self": 190.54675091198806
},
"steps_from_proto": {
"total": 30.122220560998585,
"count": 18205,
"is_parallel": true,
"self": 5.849520238947207,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.272700322051378,
"count": 182050,
"is_parallel": true,
"self": 24.272700322051378
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014081099993745738,
"count": 1,
"self": 0.00014081099993745738,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 440.01074666798695,
"count": 389971,
"is_parallel": true,
"self": 10.061911896086713,
"children": {
"process_trajectory": {
"total": 244.56038385389957,
"count": 389971,
"is_parallel": true,
"self": 243.4959474538996,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0644363999999769,
"count": 4,
"is_parallel": true,
"self": 1.0644363999999769
}
}
},
"_update_policy": {
"total": 185.38845091800067,
"count": 90,
"is_parallel": true,
"self": 67.25826816400308,
"children": {
"TorchPPOOptimizer.update": {
"total": 118.13018275399759,
"count": 4587,
"is_parallel": true,
"self": 118.13018275399759
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.24524128100006237,
"count": 1,
"self": 0.0023357420002412255,
"children": {
"RLTrainer._checkpoint": {
"total": 0.24290553899982115,
"count": 1,
"self": 0.24290553899982115
}
}
}
}
}
}
}