批量蒙特卡罗树搜索
Batch Monte Carlo Tree Search
摘要:
使用深度神经网络对一批状态进行推断比使用GPU对一个又一个状态进行推断要快得多。我们建立在这个属性,提出蒙特卡罗树搜索算法,使用批量推理。而不是使用一个搜索树或一个换位表,我们建议在同一算法中使用两者。转置表包含推理的结果,而搜索树包含蒙特卡罗树搜索的统计。我们还建议分析多个算法,提高搜索:$μ$ FPU,虚拟平均值,最后一次迭代和第二次移动算法。它们使用MobileNet神经网络进行围棋比赛的评估。
英文摘要:
Making inferences with a deep neural network on a batch of states is much faster with a GPU than making inferences on one state after another. We build on this property to propose Monte Carlo Tree Search algorithms using batched inferences. Instead of using either a search tree or a transposition table we propose to use both in the same algorithm. The transposition table contains the results of the inferences while the search tree contains the statistics of Monte Carlo Tree Search. We also propose to analyze multiple heuristics that improve the search: the $μ$ FPU, the Virtual Mean, the Last Iteration and the Second Move heuristics. They are evaluated for the game of Go using a MobileNet neural network.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。