LevinZheng's picture
First Push
98ae8c5 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8372786641120911,
"min": 0.8166351318359375,
"max": 2.8557844161987305,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7957.49658203125,
"min": 7957.49658203125,
"max": 29151.84765625,
"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": 13.104682922363281,
"min": 0.3639034330844879,
"max": 13.104682922363281,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2555.4130859375,
"min": 70.5972671508789,
"max": 2662.822265625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07140188464922281,
"min": 0.06375468454322852,
"max": 0.07510285526402774,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28560753859689125,
"min": 0.2550187381729141,
"max": 0.3755142763201387,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18565130500378563,
"min": 0.11352019398884082,
"max": 0.29089520024318316,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7426052200151425,
"min": 0.4540807759553633,
"max": 1.454476001215916,
"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": 25.522727272727273,
"min": 3.25,
"max": 25.927272727272726,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1123.0,
"min": 143.0,
"max": 1426.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.522727272727273,
"min": 3.25,
"max": 25.927272727272726,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1123.0,
"min": 143.0,
"max": 1426.0,
"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": "1748401277",
"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": "1748401723"
},
"total": 446.09815456399997,
"count": 1,
"self": 0.32241473899989614,
"children": {
"run_training.setup": {
"total": 0.023109877000024426,
"count": 1,
"self": 0.023109877000024426
},
"TrainerController.start_learning": {
"total": 445.75262994800005,
"count": 1,
"self": 0.42532679098280823,
"children": {
"TrainerController._reset_env": {
"total": 2.5641846270000315,
"count": 1,
"self": 2.5641846270000315
},
"TrainerController.advance": {
"total": 442.6693304390176,
"count": 18192,
"self": 0.44236525304904717,
"children": {
"env_step": {
"total": 317.08814189598684,
"count": 18192,
"self": 239.47197798597654,
"children": {
"SubprocessEnvManager._take_step": {
"total": 77.36777760699442,
"count": 18192,
"self": 1.354691998995122,
"children": {
"TorchPolicy.evaluate": {
"total": 76.0130856079993,
"count": 18192,
"self": 76.0130856079993
}
}
},
"workers": {
"total": 0.24838630301587727,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 444.756967929982,
"count": 18192,
"is_parallel": true,
"self": 234.61152072300138,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002490104999878895,
"count": 1,
"is_parallel": true,
"self": 0.0008047419996728422,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016853630002060527,
"count": 10,
"is_parallel": true,
"self": 0.0016853630002060527
}
}
},
"UnityEnvironment.step": {
"total": 0.04568463299983705,
"count": 1,
"is_parallel": true,
"self": 0.0007463709996500256,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004978460001439089,
"count": 1,
"is_parallel": true,
"self": 0.0004978460001439089
},
"communicator.exchange": {
"total": 0.04208610599994245,
"count": 1,
"is_parallel": true,
"self": 0.04208610599994245
},
"steps_from_proto": {
"total": 0.002354310000100668,
"count": 1,
"is_parallel": true,
"self": 0.00043791899975076376,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001916391000349904,
"count": 10,
"is_parallel": true,
"self": 0.001916391000349904
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 210.14544720698063,
"count": 18191,
"is_parallel": true,
"self": 8.879273123989606,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.767015428987634,
"count": 18191,
"is_parallel": true,
"self": 4.767015428987634
},
"communicator.exchange": {
"total": 167.05488003900587,
"count": 18191,
"is_parallel": true,
"self": 167.05488003900587
},
"steps_from_proto": {
"total": 29.44427861499753,
"count": 18191,
"is_parallel": true,
"self": 5.680974019000132,
"children": {
"_process_rank_one_or_two_observation": {
"total": 23.763304595997397,
"count": 181910,
"is_parallel": true,
"self": 23.763304595997397
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 125.1388232899817,
"count": 18192,
"self": 0.5515323589654599,
"children": {
"process_trajectory": {
"total": 28.982894083016618,
"count": 18192,
"self": 28.544271264016743,
"children": {
"RLTrainer._checkpoint": {
"total": 0.43862281899987465,
"count": 4,
"self": 0.43862281899987465
}
}
},
"_update_policy": {
"total": 95.60439684799962,
"count": 90,
"self": 38.13994235199698,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.464454496002645,
"count": 4587,
"self": 57.464454496002645
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0929998097708449e-06,
"count": 1,
"self": 1.0929998097708449e-06
},
"TrainerController._save_models": {
"total": 0.09378699799981405,
"count": 1,
"self": 0.0011344399997597066,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09265255800005434,
"count": 1,
"self": 0.09265255800005434
}
}
}
}
}
}
}