Deyvid89's picture
First Push
a8a44db verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.865623414516449,
"min": 0.865623414516449,
"max": 2.82322359085083,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8226.884765625,
"min": 8226.884765625,
"max": 28819.466796875,
"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": 12.933146476745605,
"min": 0.39048174023628235,
"max": 12.933146476745605,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2521.963623046875,
"min": 75.75345611572266,
"max": 2609.60986328125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06884876594253286,
"min": 0.06316628008789849,
"max": 0.07589504209052608,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27539506377013145,
"min": 0.25266512035159394,
"max": 0.3794752104526304,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1995413714618075,
"min": 0.11819485169789735,
"max": 0.29061033217345966,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.79816548584723,
"min": 0.4727794067915894,
"max": 1.4530516608672983,
"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": 25.477272727272727,
"min": 3.590909090909091,
"max": 25.672727272727272,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1121.0,
"min": 158.0,
"max": 1412.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.477272727272727,
"min": 3.590909090909091,
"max": 25.672727272727272,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1121.0,
"min": 158.0,
"max": 1412.0,
"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": "1770754283",
"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": "1770754923"
},
"total": 639.3872370100007,
"count": 1,
"self": 0.5423454600004334,
"children": {
"run_training.setup": {
"total": 0.04574853600024653,
"count": 1,
"self": 0.04574853600024653
},
"TrainerController.start_learning": {
"total": 638.799143014,
"count": 1,
"self": 0.698097022017464,
"children": {
"TrainerController._reset_env": {
"total": 4.4160038310001255,
"count": 1,
"self": 4.4160038310001255
},
"TrainerController.advance": {
"total": 633.6080359939797,
"count": 18192,
"self": 0.738886393051871,
"children": {
"env_step": {
"total": 458.7403254520086,
"count": 18192,
"self": 395.6615370799491,
"children": {
"SubprocessEnvManager._take_step": {
"total": 62.65420394208195,
"count": 18192,
"self": 2.3494357880999814,
"children": {
"TorchPolicy.evaluate": {
"total": 60.30476815398197,
"count": 18192,
"self": 60.30476815398197
}
}
},
"workers": {
"total": 0.4245844299775854,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 635.3612855329475,
"count": 18192,
"is_parallel": true,
"self": 294.1091422320742,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008163500000591739,
"count": 1,
"is_parallel": true,
"self": 0.005838652000420552,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002324848000171187,
"count": 10,
"is_parallel": true,
"self": 0.002324848000171187
}
}
},
"UnityEnvironment.step": {
"total": 0.0527334560001691,
"count": 1,
"is_parallel": true,
"self": 0.0007390660002783989,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004912300000796677,
"count": 1,
"is_parallel": true,
"self": 0.0004912300000796677
},
"communicator.exchange": {
"total": 0.04916451400004007,
"count": 1,
"is_parallel": true,
"self": 0.04916451400004007
},
"steps_from_proto": {
"total": 0.0023386459997709608,
"count": 1,
"is_parallel": true,
"self": 0.0004276809986549779,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019109650011159829,
"count": 10,
"is_parallel": true,
"self": 0.0019109650011159829
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 341.2521433008733,
"count": 18191,
"is_parallel": true,
"self": 15.500853951938552,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.37545999797021,
"count": 18191,
"is_parallel": true,
"self": 8.37545999797021
},
"communicator.exchange": {
"total": 264.65082895891373,
"count": 18191,
"is_parallel": true,
"self": 264.65082895891373
},
"steps_from_proto": {
"total": 52.72500039205079,
"count": 18191,
"is_parallel": true,
"self": 9.646709149570597,
"children": {
"_process_rank_one_or_two_observation": {
"total": 43.07829124248019,
"count": 181910,
"is_parallel": true,
"self": 43.07829124248019
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 174.1288241489192,
"count": 18192,
"self": 0.9126372079763314,
"children": {
"process_trajectory": {
"total": 34.5174574959392,
"count": 18192,
"self": 34.00947677593831,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5079807200008872,
"count": 4,
"self": 0.5079807200008872
}
}
},
"_update_policy": {
"total": 138.69872944500366,
"count": 90,
"self": 48.920746067022264,
"children": {
"TorchPPOOptimizer.update": {
"total": 89.7779833779814,
"count": 4587,
"self": 89.7779833779814
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0150015441467986e-06,
"count": 1,
"self": 1.0150015441467986e-06
},
"TrainerController._save_models": {
"total": 0.07700515200122027,
"count": 1,
"self": 0.0011142730018036673,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0758908789994166,
"count": 1,
"self": 0.0758908789994166
}
}
}
}
}
}
}