anacg's picture
First Push
a96faa7 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9492964744567871,
"min": 0.9492964744567871,
"max": 2.8595869541168213,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9147.4208984375,
"min": 9147.4208984375,
"max": 29316.484375,
"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": 11.930387496948242,
"min": 0.42563557624816895,
"max": 11.930387496948242,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2326.425537109375,
"min": 82.57330322265625,
"max": 2412.59375,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06527931670180075,
"min": 0.06252597987755579,
"max": 0.07498462864565299,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.261117266807203,
"min": 0.25010391951022315,
"max": 0.3749231432282649,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1717596840770806,
"min": 0.12257129077196999,
"max": 0.2974510036554991,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6870387363083224,
"min": 0.49028516308787995,
"max": 1.4298913934651543,
"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": 23.022727272727273,
"min": 3.6136363636363638,
"max": 23.431818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1013.0,
"min": 159.0,
"max": 1285.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.022727272727273,
"min": 3.6136363636363638,
"max": 23.431818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1013.0,
"min": 159.0,
"max": 1285.0,
"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": "1724962143",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1724962696"
},
"total": 553.655399239,
"count": 1,
"self": 0.5279614629999969,
"children": {
"run_training.setup": {
"total": 0.0680892780000022,
"count": 1,
"self": 0.0680892780000022
},
"TrainerController.start_learning": {
"total": 553.059348498,
"count": 1,
"self": 0.7835257809960012,
"children": {
"TrainerController._reset_env": {
"total": 2.2919117479999613,
"count": 1,
"self": 2.2919117479999613
},
"TrainerController.advance": {
"total": 549.873057666004,
"count": 18216,
"self": 0.38228079600082765,
"children": {
"env_step": {
"total": 549.4907768700032,
"count": 18216,
"self": 427.54608210200445,
"children": {
"SubprocessEnvManager._take_step": {
"total": 121.55713789899448,
"count": 18216,
"self": 2.0236348389879026,
"children": {
"TorchPolicy.evaluate": {
"total": 119.53350306000658,
"count": 18216,
"self": 119.53350306000658
}
}
},
"workers": {
"total": 0.3875568690042428,
"count": 18216,
"self": 0.0,
"children": {
"worker_root": {
"total": 551.4112274499965,
"count": 18216,
"is_parallel": true,
"self": 252.76489695500038,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0030298650000304406,
"count": 1,
"is_parallel": true,
"self": 0.0012189260001491675,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001810938999881273,
"count": 10,
"is_parallel": true,
"self": 0.001810938999881273
}
}
},
"UnityEnvironment.step": {
"total": 0.04355627199998935,
"count": 1,
"is_parallel": true,
"self": 0.0008118699999499768,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004578770000307486,
"count": 1,
"is_parallel": true,
"self": 0.0004578770000307486
},
"communicator.exchange": {
"total": 0.03986892099999295,
"count": 1,
"is_parallel": true,
"self": 0.03986892099999295
},
"steps_from_proto": {
"total": 0.0024176040000156718,
"count": 1,
"is_parallel": true,
"self": 0.0005236770000465185,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018939269999691533,
"count": 10,
"is_parallel": true,
"self": 0.0018939269999691533
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 298.64633049499616,
"count": 18215,
"is_parallel": true,
"self": 14.127294075983912,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.055047854005693,
"count": 18215,
"is_parallel": true,
"self": 7.055047854005693
},
"communicator.exchange": {
"total": 234.36325289299958,
"count": 18215,
"is_parallel": true,
"self": 234.36325289299958
},
"steps_from_proto": {
"total": 43.10073567200698,
"count": 18215,
"is_parallel": true,
"self": 8.285109142001431,
"children": {
"_process_rank_one_or_two_observation": {
"total": 34.815626530005545,
"count": 182150,
"is_parallel": true,
"self": 34.815626530005545
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00024227599999449012,
"count": 1,
"self": 0.00024227599999449012,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 543.7789701280167,
"count": 735649,
"is_parallel": true,
"self": 15.621753778023276,
"children": {
"process_trajectory": {
"total": 295.48655741199383,
"count": 735649,
"is_parallel": true,
"self": 294.5688315539937,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9177258580001535,
"count": 4,
"is_parallel": true,
"self": 0.9177258580001535
}
}
},
"_update_policy": {
"total": 232.67065893799952,
"count": 90,
"is_parallel": true,
"self": 69.72281496899592,
"children": {
"TorchPPOOptimizer.update": {
"total": 162.9478439690036,
"count": 4587,
"is_parallel": true,
"self": 162.9478439690036
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11061102700000447,
"count": 1,
"self": 0.001423676000058549,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10918735099994592,
"count": 1,
"self": 0.10918735099994592
}
}
}
}
}
}
}