arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.10758cs.GTcs.DMcs.DScs.MA
收藏

抽样均衡:结构化博弈中的快速无悔学习

Sampling Equilibria: Fast No-Regret Learning in Structured Games

Daniel Beaglehole, Max Hopkins, Daniel Kane, Sihan Liu, Shachar Lovett

摘要:

游戏中的学习和均衡计算是计算机科学和经济学的基本问题,其应用范围从政治到机器学习。这一领域的大部分工作都围绕着一个名为\emph{randomized weighted majority}(RWM)的简单算法,也称为“对冲”或“乘法权重更新”,众所周知,它可以在对抗环境中实现统计上的最佳速率(Littlestone和Warren '94,Freund和Schapire '99)。不幸的是,RWM有一个固有的计算障碍:它需要在所有可能的动作上维护和采样分布。在典型的感兴趣的设置中,动作空间是指数级的大,似乎使RWM在实践中无用。在这项工作中,我们反驳了这一概念的各种\emph{structured}游戏,显示它是可能的有效地(近似)采样的动作空间在RWM中的\emph{polylogarithmic}时间。这给出了用于诸如\emph{(discrete) Colonel Blotto game}、\emph{matroid congestion}、\emph{matroid security}和基本\emph{dueling games}等问题的第一个有效的无遗憾算法。作为一个直接的推论,我们给出了一个多对数时间元算法来计算近似纳什均衡这些游戏是指数速度比以前的方法在几个重要的设置。此外,我们的算法是第一个有效地计算均衡,这些游戏的一般总和,两个以上的球员,并为上校布洛托,多种资源类型的更多参与的变种。

英文摘要:

Learning and equilibrium computation in games are fundamental problems across computer science and economics, with applications ranging from politics to machine learning. Much of the work in this area revolves around a simple algorithm termed \emph{randomized weighted majority} (RWM), also known as "Hedge" or "Multiplicative Weights Update," which is well known to achieve statistically optimal rates in adversarial settings (Littlestone and Warmuth '94, Freund and Schapire '99). Unfortunately, RWM comes with an inherent computational barrier: it requires maintaining and sampling from a distribution over all possible actions. In typical settings of interest the action space is exponentially large, seemingly rendering RWM useless in practice. In this work, we refute this notion for a broad variety of \emph{structured} games, showing it is possible to efficiently (approximately) sample the action space in RWM in \emph{polylogarithmic} time. This gives the first efficient no-regret algorithms for problems such as the \emph{(discrete) Colonel Blotto game}, \emph{matroid congestion}, \emph{matroid security}, and basic \emph{dueling games}. As an immediate corollary, we give a polylogarithmic time meta-algorithm to compute approximate Nash Equilibria for these games that is exponentially faster than prior methods in several important settings. Further, our algorithm is the first to efficiently compute equilibria for more involved variants of these games with general sums, more than two players, and, for Colonel Blotto, multiple resource types.

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。

↑