HuggingDLRL's picture
snowball
711bffd verified
Raw
History Blame Contribute Delete
17.5 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.92120760679245,
"min": 0.92120760679245,
"max": 2.8427515029907227,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8755.1572265625,
"min": 8755.1572265625,
"max": 29018.806640625,
"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": 12.656865119934082,
"min": 0.46754685044288635,
"max": 12.656865119934082,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2468.088623046875,
"min": 90.70408630371094,
"max": 2550.849609375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0694291366085321,
"min": 0.06132167421336121,
"max": 0.07475225030979274,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2777165464341284,
"min": 0.2588739478681008,
"max": 0.3632932749707264,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2152939705433799,
"min": 0.14588702851381408,
"max": 0.2807385239531012,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8611758821735196,
"min": 0.5835481140552563,
"max": 1.4036926197655062,
"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": 24.977272727272727,
"min": 4.159090909090909,
"max": 25.145454545454545,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1099.0,
"min": 183.0,
"max": 1383.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.977272727272727,
"min": 4.159090909090909,
"max": 25.145454545454545,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1099.0,
"min": 183.0,
"max": 1383.0,
"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": "1742025063",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1742025490"
},
"total": 426.376104176,
"count": 1,
"self": 0.43677691599998525,
"children": {
"run_training.setup": {
"total": 0.0329575969999496,
"count": 1,
"self": 0.0329575969999496
},
"TrainerController.start_learning": {
"total": 425.9063696630001,
"count": 1,
"self": 0.3255301920044076,
"children": {
"TrainerController._reset_env": {
"total": 3.333829605999995,
"count": 1,
"self": 3.333829605999995
},
"TrainerController.advance": {
"total": 422.1603769019956,
"count": 18192,
"self": 0.37221778398361494,
"children": {
"env_step": {
"total": 299.9666572900078,
"count": 18192,
"self": 228.22914828500336,
"children": {
"SubprocessEnvManager._take_step": {
"total": 71.53638472399632,
"count": 18192,
"self": 1.2480188219954016,
"children": {
"TorchPolicy.evaluate": {
"total": 70.28836590200092,
"count": 18192,
"self": 70.28836590200092
}
}
},
"workers": {
"total": 0.20112428100810575,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 424.51350210700514,
"count": 18192,
"is_parallel": true,
"self": 223.96160297000358,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00653696899996703,
"count": 1,
"is_parallel": true,
"self": 0.004414979000102903,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021219899998641267,
"count": 10,
"is_parallel": true,
"self": 0.0021219899998641267
}
}
},
"UnityEnvironment.step": {
"total": 0.036703599000020404,
"count": 1,
"is_parallel": true,
"self": 0.0005833920000668513,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039982999999210733,
"count": 1,
"is_parallel": true,
"self": 0.00039982999999210733
},
"communicator.exchange": {
"total": 0.03388986200002364,
"count": 1,
"is_parallel": true,
"self": 0.03388986200002364
},
"steps_from_proto": {
"total": 0.0018305149999378045,
"count": 1,
"is_parallel": true,
"self": 0.0003959819999863612,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014345329999514433,
"count": 10,
"is_parallel": true,
"self": 0.0014345329999514433
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 200.55189913700156,
"count": 18191,
"is_parallel": true,
"self": 9.748363306002148,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.3081756159919,
"count": 18191,
"is_parallel": true,
"self": 5.3081756159919
},
"communicator.exchange": {
"total": 154.0795251460071,
"count": 18191,
"is_parallel": true,
"self": 154.0795251460071
},
"steps_from_proto": {
"total": 31.415835069000423,
"count": 18191,
"is_parallel": true,
"self": 5.653375848998394,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.76245922000203,
"count": 181910,
"is_parallel": true,
"self": 25.76245922000203
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 121.82150182800422,
"count": 18192,
"self": 0.39365798500875826,
"children": {
"process_trajectory": {
"total": 26.931310541995458,
"count": 18192,
"self": 26.482254634995456,
"children": {
"RLTrainer._checkpoint": {
"total": 0.44905590700000175,
"count": 4,
"self": 0.44905590700000175
}
}
},
"_update_policy": {
"total": 94.496533301,
"count": 90,
"self": 37.42040259500436,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.07613070599564,
"count": 4587,
"self": 57.07613070599564
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.86999941940303e-07,
"count": 1,
"self": 8.86999941940303e-07
},
"TrainerController._save_models": {
"total": 0.08663207600011447,
"count": 1,
"self": 0.000972717000195189,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08565935899991928,
"count": 1,
"self": 0.08565935899991928
}
}
}
}
}
}
}