0ybo's picture
First Push
304bd3b verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9232752919197083,
"min": 0.9114676117897034,
"max": 2.8466408252716064,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8774.80859375,
"min": 8774.80859375,
"max": 29058.509765625,
"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": 12.507847785949707,
"min": 0.2949874699115753,
"max": 12.507847785949707,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2439.0302734375,
"min": 57.227569580078125,
"max": 2519.2080078125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0642843114907794,
"min": 0.06341127609245151,
"max": 0.0763041094676951,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2571372459631176,
"min": 0.25364510436980603,
"max": 0.3694823642133498,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18583230893401542,
"min": 0.15046790885047384,
"max": 0.26184513323447284,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7433292357360617,
"min": 0.6018716354018954,
"max": 1.3092256661723642,
"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": 24.522727272727273,
"min": 3.977272727272727,
"max": 25.10909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1079.0,
"min": 175.0,
"max": 1381.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.522727272727273,
"min": 3.977272727272727,
"max": 25.10909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1079.0,
"min": 175.0,
"max": 1381.0,
"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": "1745975434",
"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": "1745975867"
},
"total": 432.961553996,
"count": 1,
"self": 0.43581577200006905,
"children": {
"run_training.setup": {
"total": 0.03407810199996675,
"count": 1,
"self": 0.03407810199996675
},
"TrainerController.start_learning": {
"total": 432.491660122,
"count": 1,
"self": 0.35159358099349447,
"children": {
"TrainerController._reset_env": {
"total": 3.3016258860000107,
"count": 1,
"self": 3.3016258860000107
},
"TrainerController.advance": {
"total": 428.7536549500064,
"count": 18192,
"self": 0.3819362229960461,
"children": {
"env_step": {
"total": 307.00367304700876,
"count": 18192,
"self": 235.39909654102644,
"children": {
"SubprocessEnvManager._take_step": {
"total": 71.39814846798868,
"count": 18192,
"self": 1.3145328889745542,
"children": {
"TorchPolicy.evaluate": {
"total": 70.08361557901412,
"count": 18192,
"self": 70.08361557901412
}
}
},
"workers": {
"total": 0.20642803799364629,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 431.04159227695936,
"count": 18192,
"is_parallel": true,
"self": 224.4566688669522,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005499344000099882,
"count": 1,
"is_parallel": true,
"self": 0.003952097000137655,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015472469999622263,
"count": 10,
"is_parallel": true,
"self": 0.0015472469999622263
}
}
},
"UnityEnvironment.step": {
"total": 0.03611938700009887,
"count": 1,
"is_parallel": true,
"self": 0.0005527220000658417,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042635499994503334,
"count": 1,
"is_parallel": true,
"self": 0.00042635499994503334
},
"communicator.exchange": {
"total": 0.033200715000020864,
"count": 1,
"is_parallel": true,
"self": 0.033200715000020864
},
"steps_from_proto": {
"total": 0.0019395950000671291,
"count": 1,
"is_parallel": true,
"self": 0.0004166529997746693,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015229420002924599,
"count": 10,
"is_parallel": true,
"self": 0.0015229420002924599
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 206.58492341000715,
"count": 18191,
"is_parallel": true,
"self": 9.843644129955464,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.701463535016728,
"count": 18191,
"is_parallel": true,
"self": 5.701463535016728
},
"communicator.exchange": {
"total": 158.29233383202723,
"count": 18191,
"is_parallel": true,
"self": 158.29233383202723
},
"steps_from_proto": {
"total": 32.74748191300773,
"count": 18191,
"is_parallel": true,
"self": 5.927561146063226,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.819920766944506,
"count": 181910,
"is_parallel": true,
"self": 26.819920766944506
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 121.36804568000161,
"count": 18192,
"self": 0.44826988200338747,
"children": {
"process_trajectory": {
"total": 27.94288880999875,
"count": 18192,
"self": 27.5139977599988,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4288910499999474,
"count": 4,
"self": 0.4288910499999474
}
}
},
"_update_policy": {
"total": 92.97688698799948,
"count": 90,
"self": 37.93280021199621,
"children": {
"TorchPPOOptimizer.update": {
"total": 55.04408677600327,
"count": 4587,
"self": 55.04408677600327
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.600000794307562e-07,
"count": 1,
"self": 9.600000794307562e-07
},
"TrainerController._save_models": {
"total": 0.08478474499997901,
"count": 1,
"self": 0.0008192410000447126,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0839655039999343,
"count": 1,
"self": 0.0839655039999343
}
}
}
}
}
}
}