luyi0619's picture
First Push
e21c81b verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8089478611946106,
"min": 0.8003692030906677,
"max": 2.848808765411377,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7688.240234375,
"min": 7688.240234375,
"max": 29080.640625,
"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": 12.675750732421875,
"min": 0.5561818480491638,
"max": 12.710165977478027,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2471.771484375,
"min": 107.89927673339844,
"max": 2592.873779296875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07784129409051008,
"min": 0.06389835135276228,
"max": 0.07784129409051008,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3113651763620403,
"min": 0.25559340541104913,
"max": 0.36915696792629227,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2151999184679167,
"min": 0.13668774340904372,
"max": 0.32164234811184456,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8607996738716668,
"min": 0.5467509736361749,
"max": 1.6082117405592227,
"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": 24.75,
"min": 3.75,
"max": 25.054545454545455,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1089.0,
"min": 165.0,
"max": 1378.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.75,
"min": 3.75,
"max": 25.054545454545455,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1089.0,
"min": 165.0,
"max": 1378.0,
"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": "1747956300",
"python_version": "3.10.12 (main, Feb 4 2025, 14:57:36) [GCC 11.4.0]",
"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": "1747956718"
},
"total": 417.9394847140002,
"count": 1,
"self": 0.4352017109999906,
"children": {
"run_training.setup": {
"total": 0.021919403000083548,
"count": 1,
"self": 0.021919403000083548
},
"TrainerController.start_learning": {
"total": 417.4823636000001,
"count": 1,
"self": 0.34174545700147974,
"children": {
"TrainerController._reset_env": {
"total": 3.38908117699998,
"count": 1,
"self": 3.38908117699998
},
"TrainerController.advance": {
"total": 413.6720164419985,
"count": 18192,
"self": 0.35108353401074055,
"children": {
"env_step": {
"total": 290.930348422989,
"count": 18192,
"self": 221.9727838809804,
"children": {
"SubprocessEnvManager._take_step": {
"total": 68.7537652950034,
"count": 18192,
"self": 1.2181886909968398,
"children": {
"TorchPolicy.evaluate": {
"total": 67.53557660400656,
"count": 18192,
"self": 67.53557660400656
}
}
},
"workers": {
"total": 0.20379924700523588,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 416.0478981160063,
"count": 18192,
"is_parallel": true,
"self": 221.31624395601239,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005232678000083979,
"count": 1,
"is_parallel": true,
"self": 0.0036700420002944156,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015626359997895634,
"count": 10,
"is_parallel": true,
"self": 0.0015626359997895634
}
}
},
"UnityEnvironment.step": {
"total": 0.035700390000101834,
"count": 1,
"is_parallel": true,
"self": 0.000616686000057598,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041296099993815005,
"count": 1,
"is_parallel": true,
"self": 0.00041296099993815005
},
"communicator.exchange": {
"total": 0.03275083900007303,
"count": 1,
"is_parallel": true,
"self": 0.03275083900007303
},
"steps_from_proto": {
"total": 0.001919904000033057,
"count": 1,
"is_parallel": true,
"self": 0.00039807100029065623,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015218329997424007,
"count": 10,
"is_parallel": true,
"self": 0.0015218329997424007
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 194.73165415999392,
"count": 18191,
"is_parallel": true,
"self": 9.645021475975454,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.297997474992826,
"count": 18191,
"is_parallel": true,
"self": 5.297997474992826
},
"communicator.exchange": {
"total": 148.25682219100804,
"count": 18191,
"is_parallel": true,
"self": 148.25682219100804
},
"steps_from_proto": {
"total": 31.5318130180176,
"count": 18191,
"is_parallel": true,
"self": 5.5250805050006875,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.006732513016914,
"count": 181910,
"is_parallel": true,
"self": 26.006732513016914
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 122.39058448499873,
"count": 18192,
"self": 0.4173699949951697,
"children": {
"process_trajectory": {
"total": 27.166180491002706,
"count": 18192,
"self": 26.723552633002555,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4426278580001508,
"count": 4,
"self": 0.4426278580001508
}
}
},
"_update_policy": {
"total": 94.80703399900085,
"count": 90,
"self": 38.714593084999024,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.09244091400183,
"count": 4587,
"self": 56.09244091400183
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.409999736613827e-07,
"count": 1,
"self": 8.409999736613827e-07
},
"TrainerController._save_models": {
"total": 0.07951968300017143,
"count": 1,
"self": 0.0007796430002144916,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07874003999995693,
"count": 1,
"self": 0.07874003999995693
}
}
}
}
}
}
}