arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1804.04789cs.GTcs.AIcs.MAecon.TH
收藏

三人不完全信息对策的成功纳什均衡代理

Successful Nash Equilibrium Agent for a 3-Player Imperfect-Information Game

Ganzfried Research(甘茨弗里德研究公司);Florida International University(佛罗里达国际大学)

Sam Ganzfried, Austin Nowak, Joannier Pinales

摘要:

为超过两个玩家的游戏创建强大的代理是AI中的一个主要开放问题。常见的方法是基于近似博弈论的解决方案的概念,如纳什均衡,这在两个玩家的零和游戏有很强的理论保证,但在非零和游戏或游戏中有两个以上的球员没有保证。我们描述了一个代理,能够击败各种现实的对手,使用一个确切的纳什均衡策略中的3人信息博弈。这表明,尽管缺乏理论保证,但基于纳什均衡策略的代理人毕竟可以在多人游戏中取得成功。

英文摘要:

Creating strong agents for games with more than two players is a major open problem in AI. Common approaches are based on approximating game-theoretic solution concepts such as Nash equilibrium, which have strong theoretical guarantees in two-player zero-sum games, but no guarantees in non-zero-sum games or in games with more than two players. We describe an agent that is able to defeat a variety of realistic opponents using an exact Nash equilibrium strategy in a 3-player imperfect-information game. This shows that, despite a lack of theoretical guarantees, agents based on Nash equilibrium strategies can be successful in multiplayer games after all.

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。

↑