makataomu's picture
First Push
d2f5dd1 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.4483032822608948,
"min": 0.41362011432647705,
"max": 2.8707406520843506,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 4300.125,
"min": 4100.62353515625,
"max": 29304.521484375,
"count": 50
},
"SnowballTarget.Step.mean": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Step.sum": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.505634307861328,
"min": 0.3507351875305176,
"max": 13.68295669555664,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2768.655029296875,
"min": 68.0426254272461,
"max": 2802.951171875,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06784871201551355,
"min": 0.06127218125670077,
"max": 0.07679153472303832,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3392435600775678,
"min": 0.25060761542636995,
"max": 0.3839576736151916,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17971195523061004,
"min": 0.11925838996459931,
"max": 0.2993789575263566,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8985597761530502,
"min": 0.47703355985839724,
"max": 1.496894787631783,
"count": 50
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.017954755269152e-06,
"min": 1.017954755269152e-06,
"max": 9.894246393456348e-05,
"count": 50
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 5.08977377634576e-06,
"min": 5.08977377634576e-06,
"max": 0.0004848098412164843,
"count": 50
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10063160502925647,
"min": 0.10063160502925647,
"max": 0.1613962791293042,
"count": 50
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5031580251462824,
"min": 0.40744221397680497,
"max": 0.800836653321797,
"count": 50
},
"SnowballTarget.Policy.Beta.mean": {
"value": 1.02957878785736e-05,
"min": 1.02957878785736e-05,
"max": 3.875258162106126e-05,
"count": 50
},
"SnowballTarget.Policy.Beta.sum": {
"value": 5.1478939392868e-05,
"min": 4.348527415413611e-05,
"max": 0.00019088525480550418,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.472727272727273,
"min": 3.3636363636363638,
"max": 27.045454545454547,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1456.0,
"min": 148.0,
"max": 1476.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.472727272727273,
"min": 3.3636363636363638,
"max": 27.045454545454547,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1456.0,
"min": 148.0,
"max": 1476.0,
"count": 50
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1750350829",
"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/SnowballBest_bd2079.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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1750351870"
},
"total": 1041.13131131,
"count": 1,
"self": 0.3297438449994843,
"children": {
"run_training.setup": {
"total": 0.02314258800015523,
"count": 1,
"self": 0.02314258800015523
},
"TrainerController.start_learning": {
"total": 1040.7784248770004,
"count": 1,
"self": 1.1458872619855356,
"children": {
"TrainerController._reset_env": {
"total": 2.11696193600028,
"count": 1,
"self": 2.11696193600028
},
"TrainerController.advance": {
"total": 1037.3571670710144,
"count": 45464,
"self": 1.1555557740157383,
"children": {
"env_step": {
"total": 742.3495725109524,
"count": 45464,
"self": 556.5377971028852,
"children": {
"SubprocessEnvManager._take_step": {
"total": 185.13356411003952,
"count": 45464,
"self": 3.4609403381491575,
"children": {
"TorchPolicy.evaluate": {
"total": 181.67262377189036,
"count": 45464,
"self": 181.67262377189036
}
}
},
"workers": {
"total": 0.6782112980276906,
"count": 45464,
"self": 0.0,
"children": {
"worker_root": {
"total": 1038.304724019104,
"count": 45464,
"is_parallel": true,
"self": 556.4977692340876,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002115740000135702,
"count": 1,
"is_parallel": true,
"self": 0.0006532810007229273,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014624589994127746,
"count": 10,
"is_parallel": true,
"self": 0.0014624589994127746
}
}
},
"UnityEnvironment.step": {
"total": 0.02608521299998756,
"count": 1,
"is_parallel": true,
"self": 0.00038965900012044585,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004181449999123288,
"count": 1,
"is_parallel": true,
"self": 0.0004181449999123288
},
"communicator.exchange": {
"total": 0.02413010199961718,
"count": 1,
"is_parallel": true,
"self": 0.02413010199961718
},
"steps_from_proto": {
"total": 0.0011473070003376051,
"count": 1,
"is_parallel": true,
"self": 0.0002364370011491701,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000910869999188435,
"count": 10,
"is_parallel": true,
"self": 0.000910869999188435
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 481.8069547850164,
"count": 45463,
"is_parallel": true,
"self": 18.04626162823797,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 9.886846095881992,
"count": 45463,
"is_parallel": true,
"self": 9.886846095881992
},
"communicator.exchange": {
"total": 396.2314913669211,
"count": 45463,
"is_parallel": true,
"self": 396.2314913669211
},
"steps_from_proto": {
"total": 57.64235569397533,
"count": 45463,
"is_parallel": true,
"self": 11.184518136066345,
"children": {
"_process_rank_one_or_two_observation": {
"total": 46.45783755790899,
"count": 454630,
"is_parallel": true,
"self": 46.45783755790899
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 293.85203878604625,
"count": 45464,
"self": 1.5015806040960342,
"children": {
"process_trajectory": {
"total": 65.18776191494317,
"count": 45464,
"self": 63.59943688394378,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5883250309993855,
"count": 10,
"self": 1.5883250309993855
}
}
},
"_update_policy": {
"total": 227.16269626700705,
"count": 227,
"self": 86.6826447810181,
"children": {
"TorchPPOOptimizer.update": {
"total": 140.48005148598895,
"count": 11574,
"self": 140.48005148598895
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.830000635702163e-07,
"count": 1,
"self": 9.830000635702163e-07
},
"TrainerController._save_models": {
"total": 0.15840762500010896,
"count": 1,
"self": 0.002622144999804732,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15578548000030423,
"count": 1,
"self": 0.15578548000030423
}
}
}
}
}
}
}