arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1807.06170cs.GTcs.LG
收藏

从最佳反应函数学习凸划分和计算博弈均衡

Learning Convex Partitions and Computing Game-theoretic Equilibria from Best Response Queries

University of Oxford(牛津大学)

Paul W. Goldberg, Francisco J. Marmolejo-Cossío

摘要:

假设一个$m$ -单纯形被划分为具有不相交内部和不同标签的$n$凸区域,我们可以通过查询它来学习任何点的标签。学习的目标是知道,对于单纯形中的任何点,在距离该点$ε$一定距离内出现的标签。我们提出了两种算法,这个任务:恒定维广义二进制搜索(CD-GBS),其中恒定$m$使用$poly(n, \log \left( \frac{1}ε \right))$查询,和恒定区域广义二进制搜索(CR-GBS),它使用CD-GBS作为一个子程序和恒定$n$使用$poly(m, \log \left( \frac{1}ε \right))$查询。我们表明,通过角谷的不动点定理,这些算法提供的最佳响应的查询复杂性计算近似良好的支持平衡的双矩阵游戏,其中一个球员有一个恒定数量的纯策略的界限。我们还部分扩展我们的结果,多个玩家的游戏,建立进一步的查询复杂性的界限计算近似良好的支持均衡在这种情况下。

英文摘要:

Suppose that an $m$-simplex is partitioned into $n$ convex regions having disjoint interiors and distinct labels, and we may learn the label of any point by querying it. The learning objective is to know, for any point in the simplex, a label that occurs within some distance $ε$ from that point. We present two algorithms for this task: Constant-Dimension Generalised Binary Search (CD-GBS), which for constant $m$ uses $poly(n, \log \left( \frac{1}ε \right))$ queries, and Constant-Region Generalised Binary Search (CR-GBS), which uses CD-GBS as a subroutine and for constant $n$ uses $poly(m, \log \left( \frac{1}ε \right))$ queries. We show via Kakutani's fixed-point theorem that these algorithms provide bounds on the best-response query complexity of computing approximate well-supported equilibria of bimatrix games in which one of the players has a constant number of pure strategies. We also partially extend our results to games with multiple players, establishing further query complexity bounds for computing approximate well-supported equilibria in this setting.

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。

↑