jiahaowang's picture
First Push
c7ed9b6 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9328668713569641,
"min": 0.9328668713569641,
"max": 2.8532679080963135,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8865.966796875,
"min": 8865.966796875,
"max": 29126.158203125,
"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": 13.108490943908691,
"min": 0.540899395942688,
"max": 13.108490943908691,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2556.15576171875,
"min": 104.93447875976562,
"max": 2647.679443359375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07413975076176975,
"min": 0.0630414984541929,
"max": 0.07606304431335278,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.296559003047079,
"min": 0.25550303862809076,
"max": 0.38031522156676395,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19467310066901,
"min": 0.155329478775635,
"max": 0.3213668871744006,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.77869240267604,
"min": 0.62131791510254,
"max": 1.606834435872003,
"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": 25.5,
"min": 4.113636363636363,
"max": 25.84090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1122.0,
"min": 181.0,
"max": 1413.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.5,
"min": 4.113636363636363,
"max": 25.84090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1122.0,
"min": 181.0,
"max": 1413.0,
"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": "1746607288",
"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": "1746607723"
},
"total": 434.91803743699984,
"count": 1,
"self": 0.43852882199917076,
"children": {
"run_training.setup": {
"total": 0.020377177000227675,
"count": 1,
"self": 0.020377177000227675
},
"TrainerController.start_learning": {
"total": 434.45913143800044,
"count": 1,
"self": 0.37987356196390465,
"children": {
"TrainerController._reset_env": {
"total": 2.1025849910001853,
"count": 1,
"self": 2.1025849910001853
},
"TrainerController.advance": {
"total": 431.8935592060361,
"count": 18192,
"self": 0.38225700392104045,
"children": {
"env_step": {
"total": 308.3922064470871,
"count": 18192,
"self": 235.0238431862408,
"children": {
"SubprocessEnvManager._take_step": {
"total": 73.15229549383639,
"count": 18192,
"self": 1.2709675649075507,
"children": {
"TorchPolicy.evaluate": {
"total": 71.88132792892884,
"count": 18192,
"self": 71.88132792892884
}
}
},
"workers": {
"total": 0.2160677670099176,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 433.0584641050473,
"count": 18192,
"is_parallel": true,
"self": 226.85906596005862,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020061499999428634,
"count": 1,
"is_parallel": true,
"self": 0.0006402230019375565,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013659269980053068,
"count": 10,
"is_parallel": true,
"self": 0.0013659269980053068
}
}
},
"UnityEnvironment.step": {
"total": 0.033986127999924065,
"count": 1,
"is_parallel": true,
"self": 0.0005649480008287355,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039276600000448525,
"count": 1,
"is_parallel": true,
"self": 0.00039276600000448525
},
"communicator.exchange": {
"total": 0.031133063999732258,
"count": 1,
"is_parallel": true,
"self": 0.031133063999732258
},
"steps_from_proto": {
"total": 0.0018953499993585865,
"count": 1,
"is_parallel": true,
"self": 0.00036592399828805355,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001529426001070533,
"count": 10,
"is_parallel": true,
"self": 0.001529426001070533
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 206.19939814498866,
"count": 18191,
"is_parallel": true,
"self": 9.794487811083854,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.522346941015712,
"count": 18191,
"is_parallel": true,
"self": 5.522346941015712
},
"communicator.exchange": {
"total": 158.32408622194725,
"count": 18191,
"is_parallel": true,
"self": 158.32408622194725
},
"steps_from_proto": {
"total": 32.55847717094184,
"count": 18191,
"is_parallel": true,
"self": 5.928243103144268,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.630234067797574,
"count": 181910,
"is_parallel": true,
"self": 26.630234067797574
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 123.11909575502796,
"count": 18192,
"self": 0.4503644620463092,
"children": {
"process_trajectory": {
"total": 27.655052345981858,
"count": 18192,
"self": 27.264913618981154,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3901387270007035,
"count": 4,
"self": 0.3901387270007035
}
}
},
"_update_policy": {
"total": 95.01367894699979,
"count": 90,
"self": 38.72300760801136,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.29067133898843,
"count": 4587,
"self": 56.29067133898843
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3130002116668038e-06,
"count": 1,
"self": 1.3130002116668038e-06
},
"TrainerController._save_models": {
"total": 0.08311236600002303,
"count": 1,
"self": 0.0008191569995688042,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08229320900045423,
"count": 1,
"self": 0.08229320900045423
}
}
}
}
}
}
}