JTStephens's picture
First Push
0b508cb
raw
history blame
18.5 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8661801218986511,
"min": 0.8661801218986511,
"max": 2.8671863079071045,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8260.759765625,
"min": 8260.759765625,
"max": 29331.31640625,
"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": 12.57765007019043,
"min": 0.3534684181213379,
"max": 12.57765007019043,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2452.641845703125,
"min": 68.5728759765625,
"max": 2551.47509765625,
"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.Losses.PolicyLoss.mean": {
"value": 0.06332117746016735,
"min": 0.06224734195141126,
"max": 0.07526549113276368,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2532847098406694,
"min": 0.24898936780564504,
"max": 0.3641580444419364,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1916163418368966,
"min": 0.1183634707601467,
"max": 0.27517908621652454,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7664653673475864,
"min": 0.4734538830405868,
"max": 1.3470000390912973,
"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.CumulativeReward.mean": {
"value": 24.727272727272727,
"min": 3.2954545454545454,
"max": 24.90909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1088.0,
"min": 145.0,
"max": 1364.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.727272727272727,
"min": 3.2954545454545454,
"max": 24.90909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1088.0,
"min": 145.0,
"max": 1364.0,
"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": "1689280363",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1689280822"
},
"total": 459.4991406600001,
"count": 1,
"self": 0.7883720950001134,
"children": {
"run_training.setup": {
"total": 0.04390275400001542,
"count": 1,
"self": 0.04390275400001542
},
"TrainerController.start_learning": {
"total": 458.666865811,
"count": 1,
"self": 0.5404646510046405,
"children": {
"TrainerController._reset_env": {
"total": 4.175219236000004,
"count": 1,
"self": 4.175219236000004
},
"TrainerController.advance": {
"total": 453.7729951159954,
"count": 18201,
"self": 0.2497857179950529,
"children": {
"env_step": {
"total": 453.52320939800035,
"count": 18201,
"self": 331.51856606400116,
"children": {
"SubprocessEnvManager._take_step": {
"total": 121.74664670899952,
"count": 18201,
"self": 1.800205886001777,
"children": {
"TorchPolicy.evaluate": {
"total": 119.94644082299774,
"count": 18201,
"self": 119.94644082299774
}
}
},
"workers": {
"total": 0.257996624999663,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 457.1887970209993,
"count": 18201,
"is_parallel": true,
"self": 217.23748615199753,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0054732780000108505,
"count": 1,
"is_parallel": true,
"self": 0.004053217000006271,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00142006100000458,
"count": 10,
"is_parallel": true,
"self": 0.00142006100000458
}
}
},
"UnityEnvironment.step": {
"total": 0.0351252529999897,
"count": 1,
"is_parallel": true,
"self": 0.0006155749999550153,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003560390000245661,
"count": 1,
"is_parallel": true,
"self": 0.0003560390000245661
},
"communicator.exchange": {
"total": 0.03199006899998835,
"count": 1,
"is_parallel": true,
"self": 0.03199006899998835
},
"steps_from_proto": {
"total": 0.002163570000021764,
"count": 1,
"is_parallel": true,
"self": 0.00035682399999359404,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018067460000281699,
"count": 10,
"is_parallel": true,
"self": 0.0018067460000281699
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 239.95131086900176,
"count": 18200,
"is_parallel": true,
"self": 10.243952093997933,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.0487758370030065,
"count": 18200,
"is_parallel": true,
"self": 5.0487758370030065
},
"communicator.exchange": {
"total": 190.0908911170006,
"count": 18200,
"is_parallel": true,
"self": 190.0908911170006
},
"steps_from_proto": {
"total": 34.56769182100021,
"count": 18200,
"is_parallel": true,
"self": 6.074410556983594,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.493281264016616,
"count": 182000,
"is_parallel": true,
"self": 28.493281264016616
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00016039499996622908,
"count": 1,
"self": 0.00016039499996622908,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 450.3136188350118,
"count": 426631,
"is_parallel": true,
"self": 9.168731385984245,
"children": {
"process_trajectory": {
"total": 244.35880183302746,
"count": 426631,
"is_parallel": true,
"self": 243.17181827702748,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1869835559999729,
"count": 4,
"is_parallel": true,
"self": 1.1869835559999729
}
}
},
"_update_policy": {
"total": 196.7860856160001,
"count": 90,
"is_parallel": true,
"self": 78.55267687899715,
"children": {
"TorchPPOOptimizer.update": {
"total": 118.23340873700295,
"count": 4587,
"is_parallel": true,
"self": 118.23340873700295
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.17802641299999777,
"count": 1,
"self": 0.001197604000026331,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17682880899997144,
"count": 1,
"self": 0.17682880899997144
}
}
}
}
}
}
}