明智选择对手：如何引导程序化策略的合成
Choosing Well Your Opponents: How to Guide the Synthesis of Programmatic Strategies
AI总结：
针对两人零和博弈程序化策略搜索引导算法计算成本高或信号不足的问题，提出Local Learner（2L）算法主动选择参考策略增强搜索信号，实验证明其效果优于IBR、FP、DO，且合成策略在MicroRTS中胜过人类编写的竞赛冠军策略。
摘要：
本文提出Local Learner（2L，局部学习器）算法，用于提供一组参考策略，以引导两人零和博弈中程序化策略的搜索。此前的学习算法，如Iterated Best Response（IBR，迭代最优响应）、Fictitious Play（FP，虚拟博弈）和Double-Oracle（DO，双神谕），要么计算成本高昂，要么会遗漏引导搜索算法的重要信息。2L会主动选择一组参考策略以增强搜索信号。我们在三款博弈（包括颇具挑战性的实时策略博弈MicroRTS）中引导局部搜索算法合成策略，通过实验验证了所提方法的优势。结果表明，2L学习到的参考策略能提供比IBR、FP和DO更强的搜索信号。我们还模拟了一场MicroRTS锦标赛，其中使用2L的合成器表现优于最近两届MicroRTS竞赛的冠军——这些冠军均为人类程序员编写的程序化策略。
英文摘要：
This paper introduces Local Learner (2L), an algorithm for providing a set of reference strategies to guide the search for programmatic strategies in two-player zero-sum games. Previous learning algorithms, such as Iterated Best Response (IBR), Fictitious Play (FP), and Double-Oracle (DO), can be computationally expensive or miss important information for guiding search algorithms. 2L actively selects a set of reference strategies to improve the search signal. We empirically demonstrate the advantages of our approach while guiding a local search algorithm for synthesizing strategies in three games, including MicroRTS, a challenging real-time strategy game. Results show that 2L learns reference strategies that provide a stronger search signal than IBR, FP, and DO. We also simulate a tournament of MicroRTS, where a synthesizer using 2L outperformed the winners of the two latest MicroRTS competitions, which were programmatic strategies written by human programmers.
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。
