Legend005's picture
First Push
7c6fdc6 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9029237031936646,
"min": 0.9029237031936646,
"max": 2.840179204940796,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8581.38671875,
"min": 8581.38671875,
"max": 28992.548828125,
"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": 12.911022186279297,
"min": 0.44278571009635925,
"max": 12.911022186279297,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2517.6494140625,
"min": 85.90042877197266,
"max": 2626.01025390625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07025214548262096,
"min": 0.0618533243849764,
"max": 0.07820957191328418,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28100858193048384,
"min": 0.2474132975399056,
"max": 0.3521645567904902,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2210884549308057,
"min": 0.13412434550792016,
"max": 0.30339249787377376,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8843538197232228,
"min": 0.5364973820316806,
"max": 1.5169624893688687,
"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": 25.318181818181817,
"min": 3.909090909090909,
"max": 25.5,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1114.0,
"min": 172.0,
"max": 1400.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.318181818181817,
"min": 3.909090909090909,
"max": 25.5,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1114.0,
"min": 172.0,
"max": 1400.0,
"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": "1748334617",
"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": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1748335023"
},
"total": 405.67196695300004,
"count": 1,
"self": 0.4360477330003505,
"children": {
"run_training.setup": {
"total": 0.03606313999989652,
"count": 1,
"self": 0.03606313999989652
},
"TrainerController.start_learning": {
"total": 405.1998560799998,
"count": 1,
"self": 0.3171405580062583,
"children": {
"TrainerController._reset_env": {
"total": 4.191666750999957,
"count": 1,
"self": 4.191666750999957
},
"TrainerController.advance": {
"total": 400.60800009799345,
"count": 18192,
"self": 0.3387214310316722,
"children": {
"env_step": {
"total": 281.9426592299865,
"count": 18192,
"self": 215.1515651619609,
"children": {
"SubprocessEnvManager._take_step": {
"total": 66.59882604698532,
"count": 18192,
"self": 1.1806682569829263,
"children": {
"TorchPolicy.evaluate": {
"total": 65.4181577900024,
"count": 18192,
"self": 65.4181577900024
}
}
},
"workers": {
"total": 0.1922680210402632,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 403.9329998969888,
"count": 18192,
"is_parallel": true,
"self": 215.28247407904132,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.01166431299998294,
"count": 1,
"is_parallel": true,
"self": 0.00975810099953378,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001906212000449159,
"count": 10,
"is_parallel": true,
"self": 0.001906212000449159
}
}
},
"UnityEnvironment.step": {
"total": 0.034520712000130516,
"count": 1,
"is_parallel": true,
"self": 0.0005697080000572896,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004148010000335489,
"count": 1,
"is_parallel": true,
"self": 0.0004148010000335489
},
"communicator.exchange": {
"total": 0.03173522500014769,
"count": 1,
"is_parallel": true,
"self": 0.03173522500014769
},
"steps_from_proto": {
"total": 0.001800977999891984,
"count": 1,
"is_parallel": true,
"self": 0.00039645299943913415,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014045250004528498,
"count": 10,
"is_parallel": true,
"self": 0.0014045250004528498
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 188.65052581794748,
"count": 18191,
"is_parallel": true,
"self": 9.30765380194589,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.341198816961878,
"count": 18191,
"is_parallel": true,
"self": 5.341198816961878
},
"communicator.exchange": {
"total": 144.03444366501571,
"count": 18191,
"is_parallel": true,
"self": 144.03444366501571
},
"steps_from_proto": {
"total": 29.967229534024,
"count": 18191,
"is_parallel": true,
"self": 5.285185185123055,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.682044348900945,
"count": 181910,
"is_parallel": true,
"self": 24.682044348900945
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 118.3266194369753,
"count": 18192,
"self": 0.3844333519784868,
"children": {
"process_trajectory": {
"total": 26.081036657997856,
"count": 18192,
"self": 25.684415504998242,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3966211529996144,
"count": 4,
"self": 0.3966211529996144
}
}
},
"_update_policy": {
"total": 91.86114942699896,
"count": 90,
"self": 37.43802318799112,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.42312623900784,
"count": 4587,
"self": 54.42312623900784
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.770001270226203e-07,
"count": 1,
"self": 9.770001270226203e-07
},
"TrainerController._save_models": {
"total": 0.08304769599999418,
"count": 1,
"self": 0.0008014559998628101,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08224624000013137,
"count": 1,
"self": 0.08224624000013137
}
}
}
}
}
}
}