creogenus's picture
Updated model
c27659a verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9212483167648315,
"min": 0.9212483167648315,
"max": 2.867960214614868,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8755.5439453125,
"min": 8755.5439453125,
"max": 29276.138671875,
"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": 13.047025680541992,
"min": 0.4108622372150421,
"max": 13.047025680541992,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2544.169921875,
"min": 79.707275390625,
"max": 2633.585693359375,
"count": 20
},
"SnowballTarget.Policy.CuriosityValueEstimate.mean": {
"value": 1.4923017024993896,
"min": 0.42835813760757446,
"max": 2.3067188262939453,
"count": 20
},
"SnowballTarget.Policy.CuriosityValueEstimate.sum": {
"value": 290.99884033203125,
"min": 83.10147857666016,
"max": 472.87738037109375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.05358708580986951,
"min": 0.050163626572744265,
"max": 0.05840093715570137,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.21434834323947805,
"min": 0.20065450629097706,
"max": 0.28953316510887817,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.09344359091059729,
"min": 0.07468930684368719,
"max": 0.14716374164277857,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.37377436364238914,
"min": 0.29875722737474875,
"max": 0.7358187082138928,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000007e-06,
"min": 8.082097306000007e-06,
"max": 0.00029188200270599996,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400003e-05,
"min": 3.232838922400003e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10134700000000002,
"min": 0.10134700000000002,
"max": 0.148647,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.4053880000000001,
"min": 0.4053880000000001,
"max": 0.73086,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00014443060000000007,
"min": 0.00014443060000000007,
"max": 0.004864970599999999,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000003,
"min": 0.0005777224000000003,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Losses.CuriosityForwardLoss.mean": {
"value": 0.036828366963362155,
"min": 0.03671931411055001,
"max": 0.11167120106518269,
"count": 20
},
"SnowballTarget.Losses.CuriosityForwardLoss.sum": {
"value": 0.14731346785344862,
"min": 0.1471481458707289,
"max": 0.44668480426073076,
"count": 20
},
"SnowballTarget.Losses.CuriosityInverseLoss.mean": {
"value": 0.7945268078283829,
"min": 0.7945268078283829,
"max": 2.7667143807627936,
"count": 20
},
"SnowballTarget.Losses.CuriosityInverseLoss.sum": {
"value": 3.1781072313135317,
"min": 3.1781072313135317,
"max": 12.65658032243902,
"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": 26.15909090909091,
"min": 3.5681818181818183,
"max": 26.15909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1151.0,
"min": 157.0,
"max": 1409.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.15909090909091,
"min": 3.5681818181818183,
"max": 26.15909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1151.0,
"min": 157.0,
"max": 1409.0,
"count": 20
},
"SnowballTarget.Policy.CuriosityReward.mean": {
"value": 3.007300841876052,
"min": 3.007300841876052,
"max": 5.480799111859365,
"count": 20
},
"SnowballTarget.Policy.CuriosityReward.sum": {
"value": 132.32123704254627,
"min": 132.32123704254627,
"max": 301.4439511522651,
"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": "1740239025",
"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=SnowballTarget3 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1740239574"
},
"total": 549.5921344230001,
"count": 1,
"self": 0.4287719890007793,
"children": {
"run_training.setup": {
"total": 0.019638693999695533,
"count": 1,
"self": 0.019638693999695533
},
"TrainerController.start_learning": {
"total": 549.1437237399996,
"count": 1,
"self": 0.34327860703251645,
"children": {
"TrainerController._reset_env": {
"total": 1.8911703900002976,
"count": 1,
"self": 1.8911703900002976
},
"TrainerController.advance": {
"total": 546.7937669579669,
"count": 18192,
"self": 0.37333067593954183,
"children": {
"env_step": {
"total": 301.67233247603235,
"count": 18192,
"self": 230.5605755181441,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.90258636994713,
"count": 18192,
"self": 1.2418399798962128,
"children": {
"TorchPolicy.evaluate": {
"total": 69.66074639005092,
"count": 18192,
"self": 69.66074639005092
}
}
},
"workers": {
"total": 0.20917058794111654,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 547.7082383329398,
"count": 18192,
"is_parallel": true,
"self": 344.88628337088994,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0021596360002149595,
"count": 1,
"is_parallel": true,
"self": 0.0006937219995961641,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014659140006187954,
"count": 10,
"is_parallel": true,
"self": 0.0014659140006187954
}
}
},
"UnityEnvironment.step": {
"total": 0.04121166200002335,
"count": 1,
"is_parallel": true,
"self": 0.0005927939992034226,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000404823000280885,
"count": 1,
"is_parallel": true,
"self": 0.000404823000280885
},
"communicator.exchange": {
"total": 0.0383123430001433,
"count": 1,
"is_parallel": true,
"self": 0.0383123430001433
},
"steps_from_proto": {
"total": 0.001901702000395744,
"count": 1,
"is_parallel": true,
"self": 0.00036747600097442046,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015342259994213236,
"count": 10,
"is_parallel": true,
"self": 0.0015342259994213236
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 202.82195496204986,
"count": 18191,
"is_parallel": true,
"self": 9.701152280037604,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.554603005948593,
"count": 18191,
"is_parallel": true,
"self": 5.554603005948593
},
"communicator.exchange": {
"total": 155.68612461098928,
"count": 18191,
"is_parallel": true,
"self": 155.68612461098928
},
"steps_from_proto": {
"total": 31.88007506507438,
"count": 18191,
"is_parallel": true,
"self": 5.624714032102929,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.25536103297145,
"count": 181910,
"is_parallel": true,
"self": 26.25536103297145
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 244.74810380599502,
"count": 18192,
"self": 0.4115569980149303,
"children": {
"process_trajectory": {
"total": 38.8613563479812,
"count": 18192,
"self": 38.34231229598117,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5190440520000266,
"count": 4,
"self": 0.5190440520000266
}
}
},
"_update_policy": {
"total": 205.47519045999888,
"count": 90,
"self": 133.8213378710152,
"children": {
"TorchPPOOptimizer.update": {
"total": 71.65385258898368,
"count": 4945,
"self": 71.65385258898368
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1580004866118543e-06,
"count": 1,
"self": 1.1580004866118543e-06
},
"TrainerController._save_models": {
"total": 0.11550662699937675,
"count": 1,
"self": 0.0014125859997875523,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1140940409995892,
"count": 1,
"self": 0.1140940409995892
}
}
}
}
}
}
}