zpattdev's picture
first!
4aee5fc
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9502623081207275,
"min": 0.9502623081207275,
"max": 2.871805429458618,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9073.1044921875,
"min": 9073.1044921875,
"max": 29378.568359375,
"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": 13.029632568359375,
"min": 0.4002279043197632,
"max": 13.029632568359375,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2540.7783203125,
"min": 77.64421081542969,
"max": 2638.006591796875,
"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": 0.06891837841341804,
"min": 0.06349766186691055,
"max": 0.07499459377811267,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27567351365367215,
"min": 0.2592942580325625,
"max": 0.3710733478718812,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19004795758747586,
"min": 0.11494375839738138,
"max": 0.2737267905006222,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7601918303499035,
"min": 0.45977503358952554,
"max": 1.368633952503111,
"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": 26.136363636363637,
"min": 3.477272727272727,
"max": 26.136363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1150.0,
"min": 153.0,
"max": 1407.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.136363636363637,
"min": 3.477272727272727,
"max": 26.136363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1150.0,
"min": 153.0,
"max": 1407.0,
"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": "1690495085",
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1690495576"
},
"total": 490.78266691099986,
"count": 1,
"self": 0.441698100999929,
"children": {
"run_training.setup": {
"total": 0.03603544800000691,
"count": 1,
"self": 0.03603544800000691
},
"TrainerController.start_learning": {
"total": 490.30493336199993,
"count": 1,
"self": 0.6270717340038345,
"children": {
"TrainerController._reset_env": {
"total": 5.916363894000028,
"count": 1,
"self": 5.916363894000028
},
"TrainerController.advance": {
"total": 483.61828289099617,
"count": 18201,
"self": 0.2794520909961875,
"children": {
"env_step": {
"total": 483.3388308,
"count": 18201,
"self": 352.2182224099986,
"children": {
"SubprocessEnvManager._take_step": {
"total": 130.8187295049902,
"count": 18201,
"self": 1.681081834994643,
"children": {
"TorchPolicy.evaluate": {
"total": 129.13764766999554,
"count": 18201,
"self": 129.13764766999554
}
}
},
"workers": {
"total": 0.30187888501120597,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 488.5703828620034,
"count": 18201,
"is_parallel": true,
"self": 230.24826286698328,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0068668300000354066,
"count": 1,
"is_parallel": true,
"self": 0.005256424000094739,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016104059999406672,
"count": 10,
"is_parallel": true,
"self": 0.0016104059999406672
}
}
},
"UnityEnvironment.step": {
"total": 0.0687996109999176,
"count": 1,
"is_parallel": true,
"self": 0.0006269539999266271,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004029929999660453,
"count": 1,
"is_parallel": true,
"self": 0.0004029929999660453
},
"communicator.exchange": {
"total": 0.06489367699998638,
"count": 1,
"is_parallel": true,
"self": 0.06489367699998638
},
"steps_from_proto": {
"total": 0.002875987000038549,
"count": 1,
"is_parallel": true,
"self": 0.000535714000079679,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00234027299995887,
"count": 10,
"is_parallel": true,
"self": 0.00234027299995887
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 258.3221199950201,
"count": 18200,
"is_parallel": true,
"self": 10.937504689019647,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.488669854006957,
"count": 18200,
"is_parallel": true,
"self": 5.488669854006957
},
"communicator.exchange": {
"total": 206.30741033701008,
"count": 18200,
"is_parallel": true,
"self": 206.30741033701008
},
"steps_from_proto": {
"total": 35.588535114983415,
"count": 18200,
"is_parallel": true,
"self": 6.653905388958265,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.93462972602515,
"count": 182000,
"is_parallel": true,
"self": 28.93462972602515
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012319600000409991,
"count": 1,
"self": 0.00012319600000409991,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 480.02612032098637,
"count": 449260,
"is_parallel": true,
"self": 10.10713768106757,
"children": {
"process_trajectory": {
"total": 263.7550240329191,
"count": 449260,
"is_parallel": true,
"self": 262.94657456091875,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8084494720003477,
"count": 4,
"is_parallel": true,
"self": 0.8084494720003477
}
}
},
"_update_policy": {
"total": 206.1639586069997,
"count": 90,
"is_parallel": true,
"self": 77.92188288001091,
"children": {
"TorchPPOOptimizer.update": {
"total": 128.2420757269888,
"count": 4587,
"is_parallel": true,
"self": 128.2420757269888
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14309164699989196,
"count": 1,
"self": 0.0008328219998929853,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14225882499999898,
"count": 1,
"self": 0.14225882499999898
}
}
}
}
}
}
}