arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2501.19138cs.GT
收藏

一种基于对偶间隙下降的零和博弈求解方法

A Descent-based method on the Duality Gap for solving zero-sum games

Michail Fasoulakis, Evangelos Markakis, Giorgos Roussakis, Christodoulos Santorinaios

AI总结:

本文提出一种基于对偶间隙凸性下降的双人零和博弈均衡求解方法,通过最速下降最小化方向导数,实现几何收敛与改进复杂度,实验表明其性能媲美甚至超越OGDA等标准方法。

摘要:

我们专注于设计用于寻找双人零和博弈均衡的算法。尽管众所周知此类问题可以通过单个线性规划求解,但近年来受机器学习应用的推动,人们对更简单的算法产生了浓厚兴趣。我们的工作提出了这样一种方法,其灵感来自于观察到对偶间隙(min-max优化问题中评估收敛性的标准指标)在双线性零和博弈中是一个凸函数。为此,我们分析了一种基于下降的方法,其变体也曾作为子程序用于一系列近似一般非零和博弈Nash均衡的算法中。具体而言,我们通过寻找最小化对偶间隙函数方向导数的方向,研究了一种最速下降方法。我们的主要理论结果是,所推导的算法在达到近似均衡之前,实现了对偶间隙的几何递减和改进的复杂度界限。最后,我们通过实验评估对此进行了补充,提供了有前景的发现。我们的算法与一些求解零和博弈的标准方法(如OGDA(乐观梯度下降/上升))相当,甚至在某些情况下表现更优,即使每位玩家有数千种可用策略也是如此。

英文摘要:

We focus on the design of algorithms for finding equilibria in 2-player zero-sum games. Although it is well known that such problems can be solved by a single linear program, there has been a surge of interest in recent years for simpler algorithms, motivated in part by applications in machine learning. Our work proposes such a method, inspired by the observation that the duality gap (a standard metric for evaluating convergence in min-max optimization problems) is a convex function for bilinear zero-sum games. To this end, we analyze a descent-based approach, variants of which have also been used as a subroutine in a series of algorithms for approximating Nash equilibria in general non-zero-sum games. In particular, we study a steepest descent approach, by finding the direction that minimises the directional derivative of the duality gap function. Our main theoretical result is that the derived algorithms achieve a geometric decrease in the duality gap and improved complexity bounds until we reach an approximate equilibrium. Finally, we complement this with an experimental evaluation, which provides promising findings. Our algorithm is comparable with (and in some cases outperforms) some of the standard approaches for solving 0-sum games, such as OGDA (Optimistic Gradient Descent/Ascent), even with thousands of available strategies per player.

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。

↑