coke0zero's picture
First Push
8f0ff2e verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.98589026927948,
"min": 0.98589026927948,
"max": 2.8638994693756104,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9413.2802734375,
"min": 9413.2802734375,
"max": 29329.1953125,
"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": 12.861688613891602,
"min": 0.35093551874160767,
"max": 12.861688613891602,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2508.029296875,
"min": 68.08148956298828,
"max": 2595.75634765625,
"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.Losses.PolicyLoss.mean": {
"value": 0.06586977097892896,
"min": 0.06333428301777709,
"max": 0.07463954481542769,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26347908391571584,
"min": 0.2628523196550554,
"max": 0.35804754100036895,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19898839798920295,
"min": 0.09756360909737208,
"max": 0.2966911871643627,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7959535919568118,
"min": 0.3902544363894883,
"max": 1.4590151719018523,
"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": 25.34090909090909,
"min": 2.7954545454545454,
"max": 25.34090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1115.0,
"min": 123.0,
"max": 1386.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.34090909090909,
"min": 2.7954545454545454,
"max": 25.34090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1115.0,
"min": 123.0,
"max": 1386.0,
"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": "1706423554",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1706424070"
},
"total": 515.604268128,
"count": 1,
"self": 0.4905221619999338,
"children": {
"run_training.setup": {
"total": 0.08223324999994475,
"count": 1,
"self": 0.08223324999994475
},
"TrainerController.start_learning": {
"total": 515.0315127160001,
"count": 1,
"self": 0.6532321900115221,
"children": {
"TrainerController._reset_env": {
"total": 3.546180943999957,
"count": 1,
"self": 3.546180943999957
},
"TrainerController.advance": {
"total": 510.73492416998874,
"count": 18199,
"self": 0.33292478299324557,
"children": {
"env_step": {
"total": 510.4019993869955,
"count": 18199,
"self": 340.69634432098405,
"children": {
"SubprocessEnvManager._take_step": {
"total": 169.38156962900246,
"count": 18199,
"self": 1.6924026810111172,
"children": {
"TorchPolicy.evaluate": {
"total": 167.68916694799134,
"count": 18199,
"self": 167.68916694799134
}
}
},
"workers": {
"total": 0.3240854370089892,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 513.4759479499947,
"count": 18199,
"is_parallel": true,
"self": 253.4456418379923,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0060533219999570065,
"count": 1,
"is_parallel": true,
"self": 0.004373449999661716,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016798720002952905,
"count": 10,
"is_parallel": true,
"self": 0.0016798720002952905
}
}
},
"UnityEnvironment.step": {
"total": 0.042319000000020424,
"count": 1,
"is_parallel": true,
"self": 0.0008590620000177296,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004598130000204037,
"count": 1,
"is_parallel": true,
"self": 0.0004598130000204037
},
"communicator.exchange": {
"total": 0.03878626200003055,
"count": 1,
"is_parallel": true,
"self": 0.03878626200003055
},
"steps_from_proto": {
"total": 0.0022138629999517434,
"count": 1,
"is_parallel": true,
"self": 0.0004110789999458575,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001802784000005886,
"count": 10,
"is_parallel": true,
"self": 0.001802784000005886
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 260.03030611200245,
"count": 18198,
"is_parallel": true,
"self": 11.933225701979723,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.235154763014748,
"count": 18198,
"is_parallel": true,
"self": 6.235154763014748
},
"communicator.exchange": {
"total": 202.11495538200018,
"count": 18198,
"is_parallel": true,
"self": 202.11495538200018
},
"steps_from_proto": {
"total": 39.7469702650078,
"count": 18198,
"is_parallel": true,
"self": 7.492619627003251,
"children": {
"_process_rank_one_or_two_observation": {
"total": 32.25435063800455,
"count": 181980,
"is_parallel": true,
"self": 32.25435063800455
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00016593400005149306,
"count": 1,
"self": 0.00016593400005149306,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 504.0104676259982,
"count": 740547,
"is_parallel": true,
"self": 16.916400233045692,
"children": {
"process_trajectory": {
"total": 280.1536054479535,
"count": 740547,
"is_parallel": true,
"self": 279.52144745495366,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6321579929998506,
"count": 4,
"is_parallel": true,
"self": 0.6321579929998506
}
}
},
"_update_policy": {
"total": 206.94046194499902,
"count": 90,
"is_parallel": true,
"self": 71.25724272399236,
"children": {
"TorchPPOOptimizer.update": {
"total": 135.68321922100665,
"count": 4587,
"is_parallel": true,
"self": 135.68321922100665
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09700947799979076,
"count": 1,
"self": 0.001053254999760611,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09595622300003015,
"count": 1,
"self": 0.09595622300003015
}
}
}
}
}
}
}