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 2307.01441cs.GT
收藏

一种用于求解大规模零和扩展式对抗团队博弈的通用多玩家变换算法

A Generic Multi-Player Transformation Algorithm for Solving Large-Scale Zero-Sum Extensive-Form Adversarial Team Games

Chen Qiu, Yulin Wu, Weixin Huang, Botao Liu, Shaohuai Shi, Xuan Wang

AI总结:

本文提出一种通用多玩家变换算法,通过私有信息预分支将大规模零和扩展式对抗团队博弈转化为2玩家博弈,使TMECor求解等价于NE求解,将复杂度从指数级降至常数级,并在多个扑克案例中显著优于现有方法。

摘要:

近年来,许多重要的实践与理论突破都集中在事前关联场景下的对抗团队多玩家博弈(ATMGs)上。在该设定中,团队成员只允许在博弈开始前协调其策略。尽管已有求解扩展式ATMGs的算法,但先前算法所生成的博弈树规模会随着玩家数量呈指数增长。因此,如何处理接近真实世界的大规模零和扩展式ATMGs问题仍然是一个重大挑战。本文提出了一种通用的多玩家变换算法,该算法可以将任何满足ATMGs定义的多玩家博弈树变换为2玩家博弈树,从而将在大规模ATMGs中寻找带关联的团队极大极小均衡(TMECor)转化为求解2玩家博弈中的纳什均衡(NE)。为实现这一目标,我们首先引入一种名为私有信息预分支的新结构,该结构由一个临时机会节点和协调者节点组成,旨在代表团队成员为所有潜在私有信息做出决策。我们还从理论上证明,变换后的2玩家博弈中的NE等价于原始多玩家博弈中的TMECor。这项工作将动作空间和节点数量的增长从指数级显著降低到常数级。这使我们的工作在寻找TMECor方面优于所有先前最先进的算法,在不同的Kuhn Poker和Leduc Poker案例(21K3、21K4、21K6和21L33)中分别取得了182.89、168.47、694.44和233.98倍的显著改进。此外,这项工作首次实际求解了现有算法无法处理的5玩家ATMGs案例。

英文摘要:

Many recent practical and theoretical breakthroughs focus on adversarial team multi-player games (ATMGs) in ex ante correlation scenarios. In this setting, team members are allowed to coordinate their strategies only before the game starts. Although there existing algorithms for solving extensive-form ATMGs, the size of the game tree generated by the previous algorithms grows exponentially with the number of players. Therefore, how to deal with large-scale zero-sum extensive-form ATMGs problems close to the real world is still a significant challenge. In this paper, we propose a generic multi-player transformation algorithm, which can transform any multi-player game tree satisfying the definition of AMTGs into a 2-player game tree, such that finding a team-maxmin equilibrium with correlation (TMECor) in large-scale ATMGs can be transformed into solving NE in 2-player games. To achieve this goal, we first introduce a new structure named private information pre-branch, which consists of a temporary chance node and coordinator nodes and aims to make decisions for all potential private information on behalf of the team members. We also show theoretically that NE in the transformed 2-player game is equivalent TMECor in the original multi-player game. This work significantly reduces the growth of action space and nodes from exponential to constant level. This enables our work to outperform all the previous state-of-the-art algorithms in finding a TMECor, with 182.89, 168.47, 694.44, and 233.98 significant improvements in the different Kuhn Poker and Leduc Poker cases (21K3, 21K4, 21K6 and 21L33). In addition, this work first practically solves the ATMGs in a 5-player case which cannot be conducted by existing algorithms.

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。

↑