orenk's picture
First training of SnowballTarget
8140f3d
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8931583762168884,
"min": 0.8931583762168884,
"max": 2.854585647583008,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8527.8759765625,
"min": 8527.8759765625,
"max": 29233.8125,
"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": 13.007952690124512,
"min": 0.3968924283981323,
"max": 13.091656684875488,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2536.55078125,
"min": 76.99713134765625,
"max": 2670.697998046875,
"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": 0.07100432290762376,
"min": 0.06311740046287156,
"max": 0.07601293301802299,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28401729163049505,
"min": 0.25246960185148626,
"max": 0.38006466509011494,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21486576376300232,
"min": 0.13996841251968828,
"max": 0.26079971644223904,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8594630550520093,
"min": 0.5598736500787531,
"max": 1.3039985822111952,
"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": 25.068181818181817,
"min": 4.0,
"max": 25.836363636363636,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1103.0,
"min": 176.0,
"max": 1421.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.068181818181817,
"min": 4.0,
"max": 25.836363636363636,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1103.0,
"min": 176.0,
"max": 1421.0,
"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": "1674119392",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.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": "1674119811"
},
"total": 418.7688663009999,
"count": 1,
"self": 0.3851612869998462,
"children": {
"run_training.setup": {
"total": 0.1112217510001301,
"count": 1,
"self": 0.1112217510001301
},
"TrainerController.start_learning": {
"total": 418.2724832629999,
"count": 1,
"self": 0.5185320439964016,
"children": {
"TrainerController._reset_env": {
"total": 9.545125244000019,
"count": 1,
"self": 9.545125244000019
},
"TrainerController.advance": {
"total": 408.08593731700375,
"count": 18203,
"self": 0.2603385060222081,
"children": {
"env_step": {
"total": 407.82559881098155,
"count": 18203,
"self": 269.14484902298045,
"children": {
"SubprocessEnvManager._take_step": {
"total": 138.42498633500213,
"count": 18203,
"self": 1.3349735359815895,
"children": {
"TorchPolicy.evaluate": {
"total": 137.09001279902054,
"count": 18203,
"self": 31.67750823603069,
"children": {
"TorchPolicy.sample_actions": {
"total": 105.41250456298985,
"count": 18203,
"self": 105.41250456298985
}
}
}
}
},
"workers": {
"total": 0.25576345299896275,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 417.0578746050285,
"count": 18203,
"is_parallel": true,
"self": 197.6542991490221,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00731240400000388,
"count": 1,
"is_parallel": true,
"self": 0.004400741999916136,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0029116620000877447,
"count": 10,
"is_parallel": true,
"self": 0.0029116620000877447
}
}
},
"UnityEnvironment.step": {
"total": 0.03839523600004213,
"count": 1,
"is_parallel": true,
"self": 0.00035353500015844475,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004047489999265963,
"count": 1,
"is_parallel": true,
"self": 0.0004047489999265963
},
"communicator.exchange": {
"total": 0.03581913499988332,
"count": 1,
"is_parallel": true,
"self": 0.03581913499988332
},
"steps_from_proto": {
"total": 0.0018178170000737737,
"count": 1,
"is_parallel": true,
"self": 0.0004388190002373449,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013789979998364288,
"count": 10,
"is_parallel": true,
"self": 0.0013789979998364288
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 219.40357545600637,
"count": 18202,
"is_parallel": true,
"self": 8.095390610011009,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.7659888759901605,
"count": 18202,
"is_parallel": true,
"self": 4.7659888759901605
},
"communicator.exchange": {
"total": 175.3749465209978,
"count": 18202,
"is_parallel": true,
"self": 175.3749465209978
},
"steps_from_proto": {
"total": 31.167249449007386,
"count": 18202,
"is_parallel": true,
"self": 6.417839839062708,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.749409609944678,
"count": 182020,
"is_parallel": true,
"self": 24.749409609944678
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.67589998152107e-05,
"count": 1,
"self": 4.67589998152107e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 405.41043062699805,
"count": 335761,
"is_parallel": true,
"self": 8.497674311994388,
"children": {
"process_trajectory": {
"total": 234.9501814170044,
"count": 335761,
"is_parallel": true,
"self": 234.01262870900428,
"children": {
"RLTrainer._checkpoint": {
"total": 0.937552708000112,
"count": 4,
"is_parallel": true,
"self": 0.937552708000112
}
}
},
"_update_policy": {
"total": 161.96257489799927,
"count": 90,
"is_parallel": true,
"self": 41.868642213989915,
"children": {
"TorchPPOOptimizer.update": {
"total": 120.09393268400936,
"count": 4587,
"is_parallel": true,
"self": 120.09393268400936
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1228418989999227,
"count": 1,
"self": 0.0008355509999091737,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12200634800001353,
"count": 1,
"self": 0.12200634800001353
}
}
}
}
}
}
}