heesup's picture
First Push
79f8ed4 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8260207772254944,
"min": 0.8083568215370178,
"max": 2.874258279800415,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7850.50146484375,
"min": 7850.50146484375,
"max": 29340.427734375,
"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": 12.864317893981934,
"min": 0.3910345435142517,
"max": 12.892029762268066,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2508.5419921875,
"min": 75.86070251464844,
"max": 2629.97412109375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06614228152635655,
"min": 0.0626824496871004,
"max": 0.07304108948560942,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2645691261054262,
"min": 0.2507297987484016,
"max": 0.3652054474280471,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2004025551107,
"min": 0.11727908509441048,
"max": 0.2859625403787575,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8016102204428,
"min": 0.46911634037764194,
"max": 1.4298127018937876,
"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": 25.136363636363637,
"min": 3.3181818181818183,
"max": 25.618181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1106.0,
"min": 146.0,
"max": 1409.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.136363636363637,
"min": 3.3181818181818183,
"max": 25.618181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1106.0,
"min": 146.0,
"max": 1409.0,
"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": "1764198980",
"python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
"command_line_arguments": "/home/lion397@ad3.ucdavis.edu/miniforge3/envs/py310/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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1764199501"
},
"total": 520.6945536285639,
"count": 1,
"self": 0.42221298441290855,
"children": {
"run_training.setup": {
"total": 0.03148277662694454,
"count": 1,
"self": 0.03148277662694454
},
"TrainerController.start_learning": {
"total": 520.240857867524,
"count": 1,
"self": 0.48350855335593224,
"children": {
"TrainerController._reset_env": {
"total": 2.5307198334485292,
"count": 1,
"self": 2.5307198334485292
},
"TrainerController.advance": {
"total": 517.1027316600084,
"count": 18192,
"self": 0.5242605190724134,
"children": {
"env_step": {
"total": 320.50680290721357,
"count": 18192,
"self": 207.73979252576828,
"children": {
"SubprocessEnvManager._take_step": {
"total": 112.46888206340373,
"count": 18192,
"self": 1.6270868983119726,
"children": {
"TorchPolicy.evaluate": {
"total": 110.84179516509175,
"count": 18192,
"self": 110.84179516509175
}
}
},
"workers": {
"total": 0.29812831804156303,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 519.2888948917389,
"count": 18192,
"is_parallel": true,
"self": 343.83240827172995,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00195876881480217,
"count": 1,
"is_parallel": true,
"self": 0.0005729570984840393,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013858117163181305,
"count": 10,
"is_parallel": true,
"self": 0.0013858117163181305
}
}
},
"UnityEnvironment.step": {
"total": 0.032987454906105995,
"count": 1,
"is_parallel": true,
"self": 0.00038809701800346375,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003511495888233185,
"count": 1,
"is_parallel": true,
"self": 0.0003511495888233185
},
"communicator.exchange": {
"total": 0.030939849093556404,
"count": 1,
"is_parallel": true,
"self": 0.030939849093556404
},
"steps_from_proto": {
"total": 0.0013083592057228088,
"count": 1,
"is_parallel": true,
"self": 0.0003165099769830704,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009918492287397385,
"count": 10,
"is_parallel": true,
"self": 0.0009918492287397385
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 175.45648662000895,
"count": 18191,
"is_parallel": true,
"self": 6.90918636508286,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.627311464399099,
"count": 18191,
"is_parallel": true,
"self": 5.627311464399099
},
"communicator.exchange": {
"total": 138.39657284505665,
"count": 18191,
"is_parallel": true,
"self": 138.39657284505665
},
"steps_from_proto": {
"total": 24.523415945470333,
"count": 18191,
"is_parallel": true,
"self": 5.807010458782315,
"children": {
"_process_rank_one_or_two_observation": {
"total": 18.716405486688018,
"count": 181910,
"is_parallel": true,
"self": 18.716405486688018
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 196.07166823372245,
"count": 18192,
"self": 0.6250437442213297,
"children": {
"process_trajectory": {
"total": 32.21899650245905,
"count": 18192,
"self": 31.654331129044294,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5646653734147549,
"count": 4,
"self": 0.5646653734147549
}
}
},
"_update_policy": {
"total": 163.22762798704207,
"count": 90,
"self": 48.15355755388737,
"children": {
"TorchPPOOptimizer.update": {
"total": 115.0740704331547,
"count": 4587,
"self": 115.0740704331547
}
}
}
}
}
}
},
"trainer_threads": {
"total": 2.3730099201202393e-06,
"count": 1,
"self": 2.3730099201202393e-06
},
"TrainerController._save_models": {
"total": 0.12389544770121574,
"count": 1,
"self": 0.0007579568773508072,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12313749082386494,
"count": 1,
"self": 0.12313749082386494
}
}
}
}
}
}
}