sergiochw's picture
First Push
b1701bf verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8057949542999268,
"min": 0.8057949542999268,
"max": 2.8565776348114014,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7658.275390625,
"min": 7658.275390625,
"max": 29159.9453125,
"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": 13.224749565124512,
"min": 0.48967456817626953,
"max": 13.224749565124512,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2578.826171875,
"min": 94.99686431884766,
"max": 2685.41162109375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06550995143302049,
"min": 0.057235860921768925,
"max": 0.07590081872505264,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26203980573208197,
"min": 0.2289434436870757,
"max": 0.37950409362526316,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19137896750779715,
"min": 0.12083001167276033,
"max": 0.28606938702218676,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7655158700311886,
"min": 0.48332004669104134,
"max": 1.428236558156855,
"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": 26.386363636363637,
"min": 3.5681818181818183,
"max": 26.386363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1161.0,
"min": 157.0,
"max": 1417.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.386363636363637,
"min": 3.5681818181818183,
"max": 26.386363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1161.0,
"min": 157.0,
"max": 1417.0,
"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": "1745644501",
"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": "1745644911"
},
"total": 410.21061876,
"count": 1,
"self": 0.6163509089999479,
"children": {
"run_training.setup": {
"total": 0.02245695000010528,
"count": 1,
"self": 0.02245695000010528
},
"TrainerController.start_learning": {
"total": 409.57181090099994,
"count": 1,
"self": 0.3056618879877533,
"children": {
"TrainerController._reset_env": {
"total": 3.2972098860000187,
"count": 1,
"self": 3.2972098860000187
},
"TrainerController.advance": {
"total": 405.88561088601205,
"count": 18192,
"self": 0.32878961302458265,
"children": {
"env_step": {
"total": 286.27195723199657,
"count": 18192,
"self": 219.0218669240121,
"children": {
"SubprocessEnvManager._take_step": {
"total": 67.05808157599404,
"count": 18192,
"self": 1.200104575970954,
"children": {
"TorchPolicy.evaluate": {
"total": 65.85797700002308,
"count": 18192,
"self": 65.85797700002308
}
}
},
"workers": {
"total": 0.1920087319904269,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 408.11603626100714,
"count": 18192,
"is_parallel": true,
"self": 215.69661809301306,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005212880000044606,
"count": 1,
"is_parallel": true,
"self": 0.003779792999921483,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014330870001231233,
"count": 10,
"is_parallel": true,
"self": 0.0014330870001231233
}
}
},
"UnityEnvironment.step": {
"total": 0.07951125199997477,
"count": 1,
"is_parallel": true,
"self": 0.0006189779999203893,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041667499999675783,
"count": 1,
"is_parallel": true,
"self": 0.00041667499999675783
},
"communicator.exchange": {
"total": 0.07666439600006925,
"count": 1,
"is_parallel": true,
"self": 0.07666439600006925
},
"steps_from_proto": {
"total": 0.0018112029999883816,
"count": 1,
"is_parallel": true,
"self": 0.00039061200004653074,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001420590999941851,
"count": 10,
"is_parallel": true,
"self": 0.001420590999941851
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 192.41941816799408,
"count": 18191,
"is_parallel": true,
"self": 9.492555510978718,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.48159214898601,
"count": 18191,
"is_parallel": true,
"self": 5.48159214898601
},
"communicator.exchange": {
"total": 147.1258800050091,
"count": 18191,
"is_parallel": true,
"self": 147.1258800050091
},
"steps_from_proto": {
"total": 30.31939050302026,
"count": 18191,
"is_parallel": true,
"self": 5.301313617048663,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.018076885971595,
"count": 181910,
"is_parallel": true,
"self": 25.018076885971595
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 119.2848640409909,
"count": 18192,
"self": 0.37759969202352295,
"children": {
"process_trajectory": {
"total": 26.505999929966492,
"count": 18192,
"self": 26.090506561966322,
"children": {
"RLTrainer._checkpoint": {
"total": 0.41549336800017045,
"count": 4,
"self": 0.41549336800017045
}
}
},
"_update_policy": {
"total": 92.40126441900088,
"count": 90,
"self": 37.80535875798978,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.5959056610111,
"count": 4587,
"self": 54.5959056610111
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.890001481631771e-07,
"count": 1,
"self": 8.890001481631771e-07
},
"TrainerController._save_models": {
"total": 0.08332735199996932,
"count": 1,
"self": 0.0008123669999804406,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08251498499998888,
"count": 1,
"self": 0.08251498499998888
}
}
}
}
}
}
}