bingwu871's picture
First Push
edce5d0 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8284282684326172,
"min": 0.8284282684326172,
"max": 2.852633476257324,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7873.38232421875,
"min": 7873.38232421875,
"max": 29119.681640625,
"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": 13.066864013671875,
"min": 0.3697090446949005,
"max": 13.127450942993164,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2548.03857421875,
"min": 71.72355651855469,
"max": 2678.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06873542053504292,
"min": 0.06266620695948279,
"max": 0.07300308116000628,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2749416821401717,
"min": 0.25066482783793115,
"max": 0.3648792884869538,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17913937134047347,
"min": 0.14698576310640382,
"max": 0.27776837699553547,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7165574853618939,
"min": 0.5879430524256153,
"max": 1.3888418849776774,
"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": 25.272727272727273,
"min": 4.363636363636363,
"max": 26.136363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1112.0,
"min": 192.0,
"max": 1411.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.272727272727273,
"min": 4.363636363636363,
"max": 26.136363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1112.0,
"min": 192.0,
"max": 1411.0,
"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": "1747809936",
"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": "1747810375"
},
"total": 438.7303606790001,
"count": 1,
"self": 0.43399153099971954,
"children": {
"run_training.setup": {
"total": 0.02328932800014627,
"count": 1,
"self": 0.02328932800014627
},
"TrainerController.start_learning": {
"total": 438.27307982000025,
"count": 1,
"self": 0.347271218000742,
"children": {
"TrainerController._reset_env": {
"total": 3.3273816270000225,
"count": 1,
"self": 3.3273816270000225
},
"TrainerController.advance": {
"total": 434.51406951599915,
"count": 18192,
"self": 0.3750972279699454,
"children": {
"env_step": {
"total": 306.5599823040293,
"count": 18192,
"self": 234.230671507014,
"children": {
"SubprocessEnvManager._take_step": {
"total": 72.11171906801405,
"count": 18192,
"self": 1.2782766840091426,
"children": {
"TorchPolicy.evaluate": {
"total": 70.83344238400491,
"count": 18192,
"self": 70.83344238400491
}
}
},
"workers": {
"total": 0.21759172900124213,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 436.81930335898915,
"count": 18192,
"is_parallel": true,
"self": 231.51006167400487,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006378364000056536,
"count": 1,
"is_parallel": true,
"self": 0.004953407999892079,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014249560001644568,
"count": 10,
"is_parallel": true,
"self": 0.0014249560001644568
}
}
},
"UnityEnvironment.step": {
"total": 0.03482683700008238,
"count": 1,
"is_parallel": true,
"self": 0.0005418090004241094,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003935809997983597,
"count": 1,
"is_parallel": true,
"self": 0.0003935809997983597
},
"communicator.exchange": {
"total": 0.03207595100002436,
"count": 1,
"is_parallel": true,
"self": 0.03207595100002436
},
"steps_from_proto": {
"total": 0.001815495999835548,
"count": 1,
"is_parallel": true,
"self": 0.00033278999990216107,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001482705999933387,
"count": 10,
"is_parallel": true,
"self": 0.001482705999933387
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 205.30924168498427,
"count": 18191,
"is_parallel": true,
"self": 9.665473711983168,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.494051314007038,
"count": 18191,
"is_parallel": true,
"self": 5.494051314007038
},
"communicator.exchange": {
"total": 158.78292027899624,
"count": 18191,
"is_parallel": true,
"self": 158.78292027899624
},
"steps_from_proto": {
"total": 31.366796379997822,
"count": 18191,
"is_parallel": true,
"self": 5.676579633987785,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.690216746010037,
"count": 181910,
"is_parallel": true,
"self": 25.690216746010037
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 127.57898998399992,
"count": 18192,
"self": 0.42826670698968883,
"children": {
"process_trajectory": {
"total": 28.111517412009107,
"count": 18192,
"self": 27.68571984100913,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4257975709999755,
"count": 4,
"self": 0.4257975709999755
}
}
},
"_update_policy": {
"total": 99.03920586500112,
"count": 90,
"self": 40.54656113200076,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.49264473300036,
"count": 4587,
"self": 58.49264473300036
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.870001693139784e-07,
"count": 1,
"self": 8.870001693139784e-07
},
"TrainerController._save_models": {
"total": 0.08435657200016067,
"count": 1,
"self": 0.001025668000238511,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08333090399992216,
"count": 1,
"self": 0.08333090399992216
}
}
}
}
}
}
}