AkumaDachi's picture
First Push
5511bdb verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8882867693901062,
"min": 0.8882867693901062,
"max": 2.8444721698760986,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8442.27734375,
"min": 8442.27734375,
"max": 29036.373046875,
"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": 12.981117248535156,
"min": 0.3452041447162628,
"max": 12.981117248535156,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2531.31787109375,
"min": 66.9696044921875,
"max": 2634.20703125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06688115787812207,
"min": 0.06443172987828981,
"max": 0.07477777160980337,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2675246315124883,
"min": 0.26265639334907936,
"max": 0.37388885804901684,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1855173477647351,
"min": 0.13478337210721755,
"max": 0.2886518170582313,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7420693910589404,
"min": 0.5391334884288702,
"max": 1.3284322195777707,
"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": 25.636363636363637,
"min": 3.772727272727273,
"max": 25.672727272727272,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1128.0,
"min": 166.0,
"max": 1412.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.636363636363637,
"min": 3.772727272727273,
"max": 25.672727272727272,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1128.0,
"min": 166.0,
"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": "1750762902",
"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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1750763339"
},
"total": 436.65978231300005,
"count": 1,
"self": 0.4364011650000066,
"children": {
"run_training.setup": {
"total": 0.02591646700000183,
"count": 1,
"self": 0.02591646700000183
},
"TrainerController.start_learning": {
"total": 436.19746468100004,
"count": 1,
"self": 0.3669543650049718,
"children": {
"TrainerController._reset_env": {
"total": 3.388067478000039,
"count": 1,
"self": 3.388067478000039
},
"TrainerController.advance": {
"total": 432.35950548599476,
"count": 18192,
"self": 0.4027604630003907,
"children": {
"env_step": {
"total": 312.32680586900176,
"count": 18192,
"self": 239.84422823201692,
"children": {
"SubprocessEnvManager._take_step": {
"total": 72.25671532998842,
"count": 18192,
"self": 1.2645910979794053,
"children": {
"TorchPolicy.evaluate": {
"total": 70.99212423200902,
"count": 18192,
"self": 70.99212423200902
}
}
},
"workers": {
"total": 0.22586230699641874,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 434.7152486819979,
"count": 18192,
"is_parallel": true,
"self": 224.4402303199846,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007731612000043242,
"count": 1,
"is_parallel": true,
"self": 0.00642160700022032,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013100049998229224,
"count": 10,
"is_parallel": true,
"self": 0.0013100049998229224
}
}
},
"UnityEnvironment.step": {
"total": 0.042128031999936866,
"count": 1,
"is_parallel": true,
"self": 0.0006771319998506442,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004338850000067396,
"count": 1,
"is_parallel": true,
"self": 0.0004338850000067396
},
"communicator.exchange": {
"total": 0.03885167700002512,
"count": 1,
"is_parallel": true,
"self": 0.03885167700002512
},
"steps_from_proto": {
"total": 0.002165338000054362,
"count": 1,
"is_parallel": true,
"self": 0.00041384500025287707,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001751492999801485,
"count": 10,
"is_parallel": true,
"self": 0.001751492999801485
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 210.27501836201327,
"count": 18191,
"is_parallel": true,
"self": 9.911324934979007,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.65722697700528,
"count": 18191,
"is_parallel": true,
"self": 5.65722697700528
},
"communicator.exchange": {
"total": 161.87980932300536,
"count": 18191,
"is_parallel": true,
"self": 161.87980932300536
},
"steps_from_proto": {
"total": 32.82665712702362,
"count": 18191,
"is_parallel": true,
"self": 5.868731896976101,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.957925230047522,
"count": 181910,
"is_parallel": true,
"self": 26.957925230047522
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 119.62993915399261,
"count": 18192,
"self": 0.45953396997344953,
"children": {
"process_trajectory": {
"total": 26.589242561018864,
"count": 18192,
"self": 26.118486186018686,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4707563750001782,
"count": 4,
"self": 0.4707563750001782
}
}
},
"_update_policy": {
"total": 92.5811626230003,
"count": 90,
"self": 38.550264635998246,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.03089798700205,
"count": 4587,
"self": 54.03089798700205
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.021000116452342e-06,
"count": 1,
"self": 1.021000116452342e-06
},
"TrainerController._save_models": {
"total": 0.0829363310001554,
"count": 1,
"self": 0.000807401000201935,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08212892999995347,
"count": 1,
"self": 0.08212892999995347
}
}
}
}
}
}
}