João Raposo
First Push
cd2e31b verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7276564240455627,
"min": 0.7276564240455627,
"max": 2.811462163925171,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6915.646484375,
"min": 6915.646484375,
"max": 28699.40625,
"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": 12.814261436462402,
"min": 0.37499839067459106,
"max": 12.814261436462402,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2498.781005859375,
"min": 72.74968719482422,
"max": 2578.18603515625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06054306931084248,
"min": 0.06054306931084248,
"max": 0.0782285275305256,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.24217227724336993,
"min": 0.24217227724336993,
"max": 0.391142637652628,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20107650786053902,
"min": 0.14598339526941453,
"max": 0.2720024494563832,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8043060314421561,
"min": 0.5839335810776581,
"max": 1.360012247281916,
"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": 25.113636363636363,
"min": 4.068181818181818,
"max": 25.363636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1105.0,
"min": 179.0,
"max": 1395.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.113636363636363,
"min": 4.068181818181818,
"max": 25.363636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1105.0,
"min": 179.0,
"max": 1395.0,
"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": "1744482779",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1744483246"
},
"total": 467.1533680770001,
"count": 1,
"self": 0.4384610900000325,
"children": {
"run_training.setup": {
"total": 0.02528131899998698,
"count": 1,
"self": 0.02528131899998698
},
"TrainerController.start_learning": {
"total": 466.6896256680001,
"count": 1,
"self": 0.40865477402178385,
"children": {
"TrainerController._reset_env": {
"total": 2.9386922890000733,
"count": 1,
"self": 2.9386922890000733
},
"TrainerController.advance": {
"total": 463.241516943978,
"count": 18192,
"self": 0.4443700049787367,
"children": {
"env_step": {
"total": 333.47152116400343,
"count": 18192,
"self": 254.2204833430078,
"children": {
"SubprocessEnvManager._take_step": {
"total": 79.00034073899451,
"count": 18192,
"self": 1.407635099992035,
"children": {
"TorchPolicy.evaluate": {
"total": 77.59270563900247,
"count": 18192,
"self": 77.59270563900247
}
}
},
"workers": {
"total": 0.2506970820011247,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 465.0751098139867,
"count": 18192,
"is_parallel": true,
"self": 242.9559449389884,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005397758000071917,
"count": 1,
"is_parallel": true,
"self": 0.003789555000139444,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016082029999324732,
"count": 10,
"is_parallel": true,
"self": 0.0016082029999324732
}
}
},
"UnityEnvironment.step": {
"total": 0.03839387200002875,
"count": 1,
"is_parallel": true,
"self": 0.0006265529999609498,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00045884200005730236,
"count": 1,
"is_parallel": true,
"self": 0.00045884200005730236
},
"communicator.exchange": {
"total": 0.03528908299995237,
"count": 1,
"is_parallel": true,
"self": 0.03528908299995237
},
"steps_from_proto": {
"total": 0.002019394000058128,
"count": 1,
"is_parallel": true,
"self": 0.00041270900032941427,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016066849997287136,
"count": 10,
"is_parallel": true,
"self": 0.0016066849997287136
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 222.11916487499832,
"count": 18191,
"is_parallel": true,
"self": 10.528778740013877,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.111134442998718,
"count": 18191,
"is_parallel": true,
"self": 6.111134442998718
},
"communicator.exchange": {
"total": 170.52951120199566,
"count": 18191,
"is_parallel": true,
"self": 170.52951120199566
},
"steps_from_proto": {
"total": 34.94974048999006,
"count": 18191,
"is_parallel": true,
"self": 6.52762792097144,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.422112569018623,
"count": 181910,
"is_parallel": true,
"self": 28.422112569018623
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 129.32562577499584,
"count": 18192,
"self": 0.5433554720043503,
"children": {
"process_trajectory": {
"total": 29.109549281990326,
"count": 18192,
"self": 28.612173369990273,
"children": {
"RLTrainer._checkpoint": {
"total": 0.49737591200005227,
"count": 4,
"self": 0.49737591200005227
}
}
},
"_update_policy": {
"total": 99.67272102100117,
"count": 90,
"self": 39.88786776200391,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.78485325899726,
"count": 4587,
"self": 59.78485325899726
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0040000688604778e-06,
"count": 1,
"self": 1.0040000688604778e-06
},
"TrainerController._save_models": {
"total": 0.10076065700013714,
"count": 1,
"self": 0.0010616860001846362,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09969897099995251,
"count": 1,
"self": 0.09969897099995251
}
}
}
}
}
}
}