djbob's picture
First Push
6e5f266 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9886673092842102,
"min": 0.9886673092842102,
"max": 2.860060930252075,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9396.2939453125,
"min": 9396.2939453125,
"max": 29195.501953125,
"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": 12.722088813781738,
"min": 0.42237868905067444,
"max": 12.722088813781738,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2480.807373046875,
"min": 81.94146728515625,
"max": 2576.61572265625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0655324331988488,
"min": 0.06368187437034852,
"max": 0.07341337570202693,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2621297327953952,
"min": 0.2621297327953952,
"max": 0.3624762132879137,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20986094501088648,
"min": 0.13079056466756134,
"max": 0.29301129819131366,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8394437800435459,
"min": 0.5231622586702454,
"max": 1.4650564909565682,
"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": 3.8181818181818183,
"max": 25.181818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1105.0,
"min": 168.0,
"max": 1385.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.113636363636363,
"min": 3.8181818181818183,
"max": 25.181818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1105.0,
"min": 168.0,
"max": 1385.0,
"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": "1760197786",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1760198208"
},
"total": 421.9029266959999,
"count": 1,
"self": 0.4297610439999744,
"children": {
"run_training.setup": {
"total": 0.025731484999937493,
"count": 1,
"self": 0.025731484999937493
},
"TrainerController.start_learning": {
"total": 421.447434167,
"count": 1,
"self": 0.3257128569964607,
"children": {
"TrainerController._reset_env": {
"total": 2.897631570000044,
"count": 1,
"self": 2.897631570000044
},
"TrainerController.advance": {
"total": 418.14976580100335,
"count": 18192,
"self": 0.3517945990058706,
"children": {
"env_step": {
"total": 301.19175684198296,
"count": 18192,
"self": 235.80162200197208,
"children": {
"SubprocessEnvManager._take_step": {
"total": 65.18921607800507,
"count": 18192,
"self": 1.1678589130211776,
"children": {
"TorchPolicy.evaluate": {
"total": 64.0213571649839,
"count": 18192,
"self": 64.0213571649839
}
}
},
"workers": {
"total": 0.20091876200581282,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 419.526791053,
"count": 18192,
"is_parallel": true,
"self": 212.35669505900307,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004842780999979368,
"count": 1,
"is_parallel": true,
"self": 0.003236119999996845,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016066609999825232,
"count": 10,
"is_parallel": true,
"self": 0.0016066609999825232
}
}
},
"UnityEnvironment.step": {
"total": 0.03416689300001963,
"count": 1,
"is_parallel": true,
"self": 0.0005852029999005026,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039877900007923017,
"count": 1,
"is_parallel": true,
"self": 0.00039877900007923017
},
"communicator.exchange": {
"total": 0.03135260900000958,
"count": 1,
"is_parallel": true,
"self": 0.03135260900000958
},
"steps_from_proto": {
"total": 0.001830302000030315,
"count": 1,
"is_parallel": true,
"self": 0.00038148600026488566,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014488159997654293,
"count": 10,
"is_parallel": true,
"self": 0.0014488159997654293
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 207.17009599399694,
"count": 18191,
"is_parallel": true,
"self": 9.817658693998055,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.13188476898722,
"count": 18191,
"is_parallel": true,
"self": 5.13188476898722
},
"communicator.exchange": {
"total": 158.25569436600517,
"count": 18191,
"is_parallel": true,
"self": 158.25569436600517
},
"steps_from_proto": {
"total": 33.96485816500649,
"count": 18191,
"is_parallel": true,
"self": 6.300992054977087,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.663866110029403,
"count": 181910,
"is_parallel": true,
"self": 27.663866110029403
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 116.60621436001452,
"count": 18192,
"self": 0.4031399280224832,
"children": {
"process_trajectory": {
"total": 25.036359696992122,
"count": 18192,
"self": 24.465618117992335,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5707415789997867,
"count": 4,
"self": 0.5707415789997867
}
}
},
"_update_policy": {
"total": 91.16671473499991,
"count": 90,
"self": 37.65499363700678,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.51172109799313,
"count": 4587,
"self": 53.51172109799313
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.040001375775319e-07,
"count": 1,
"self": 8.040001375775319e-07
},
"TrainerController._save_models": {
"total": 0.074323134999986,
"count": 1,
"self": 0.0007060329999148962,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0736171020000711,
"count": 1,
"self": 0.0736171020000711
}
}
}
}
}
}
}