haris9873's picture
First Push
e12006e verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.853826642036438,
"min": 0.7846369743347168,
"max": 2.853642225265503,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8114.7685546875,
"min": 7610.02685546875,
"max": 29129.98046875,
"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": 11.773090362548828,
"min": 0.28463807702064514,
"max": 11.773090362548828,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2295.752685546875,
"min": 55.21978759765625,
"max": 2384.569091796875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06858868510222665,
"min": 0.06132723538116004,
"max": 0.07557288591416698,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2743547404089066,
"min": 0.24530894152464017,
"max": 0.37786442957083494,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18336016414504425,
"min": 0.12140813060835295,
"max": 0.2719567690409866,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.733440656580177,
"min": 0.4856325224334118,
"max": 1.359783845204933,
"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.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.Environment.CumulativeReward.mean": {
"value": 23.045454545454547,
"min": 3.409090909090909,
"max": 23.472727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1014.0,
"min": 150.0,
"max": 1291.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.045454545454547,
"min": 3.409090909090909,
"max": 23.472727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1014.0,
"min": 150.0,
"max": 1291.0,
"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": "1759834171",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1759834625"
},
"total": 454.7526725099999,
"count": 1,
"self": 0.6008425019999777,
"children": {
"run_training.setup": {
"total": 0.02912871900002756,
"count": 1,
"self": 0.02912871900002756
},
"TrainerController.start_learning": {
"total": 454.1227012889999,
"count": 1,
"self": 0.36252448099139656,
"children": {
"TrainerController._reset_env": {
"total": 3.169876562000013,
"count": 1,
"self": 3.169876562000013
},
"TrainerController.advance": {
"total": 450.4706225450085,
"count": 18192,
"self": 0.37126663901847223,
"children": {
"env_step": {
"total": 327.5232084569949,
"count": 18192,
"self": 255.67380376202675,
"children": {
"SubprocessEnvManager._take_step": {
"total": 71.6322717360033,
"count": 18192,
"self": 1.2968256290266709,
"children": {
"TorchPolicy.evaluate": {
"total": 70.33544610697663,
"count": 18192,
"self": 70.33544610697663
}
}
},
"workers": {
"total": 0.21713295896483942,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 452.0875856369855,
"count": 18192,
"is_parallel": true,
"self": 227.14320800197834,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006083951999926285,
"count": 1,
"is_parallel": true,
"self": 0.0043731130000423946,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017108389998838902,
"count": 10,
"is_parallel": true,
"self": 0.0017108389998838902
}
}
},
"UnityEnvironment.step": {
"total": 0.043043597999940175,
"count": 1,
"is_parallel": true,
"self": 0.0007180939998079339,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004965829999719062,
"count": 1,
"is_parallel": true,
"self": 0.0004965829999719062
},
"communicator.exchange": {
"total": 0.038905291000105535,
"count": 1,
"is_parallel": true,
"self": 0.038905291000105535
},
"steps_from_proto": {
"total": 0.0029236300000548,
"count": 1,
"is_parallel": true,
"self": 0.0005023389999223582,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0024212910001324417,
"count": 10,
"is_parallel": true,
"self": 0.0024212910001324417
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 224.94437763500719,
"count": 18191,
"is_parallel": true,
"self": 10.638130379994209,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.6205202000184045,
"count": 18191,
"is_parallel": true,
"self": 5.6205202000184045
},
"communicator.exchange": {
"total": 170.98126037299312,
"count": 18191,
"is_parallel": true,
"self": 170.98126037299312
},
"steps_from_proto": {
"total": 37.70446668200145,
"count": 18191,
"is_parallel": true,
"self": 6.725123337984201,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.979343344017252,
"count": 181910,
"is_parallel": true,
"self": 30.979343344017252
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 122.57614744899513,
"count": 18192,
"self": 0.4323104419923993,
"children": {
"process_trajectory": {
"total": 27.375835174003555,
"count": 18192,
"self": 26.921144843003503,
"children": {
"RLTrainer._checkpoint": {
"total": 0.45469033100005163,
"count": 4,
"self": 0.45469033100005163
}
}
},
"_update_policy": {
"total": 94.76800183299918,
"count": 90,
"self": 38.609634095004026,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.15836773799515,
"count": 4587,
"self": 56.15836773799515
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.314999963142327e-06,
"count": 1,
"self": 1.314999963142327e-06
},
"TrainerController._save_models": {
"total": 0.11967638600003738,
"count": 1,
"self": 0.0009757030002219835,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1187006829998154,
"count": 1,
"self": 0.1187006829998154
}
}
}
}
}
}
}