行为策略中纳什均衡的局部序贯理性刻画
A Characterization of Nash Equilibrium in Behavioral Strategies through Local Sequential Rationality
AI总结:
本文通过引入满足局部序贯理性和自独立一致性的额外行为策略与信念,刻画了扩展型博弈中的行为策略纳什均衡,并给出充要多项式系统及可微路径跟踪计算方法。
摘要:
纳什在《纳什(1951)》中通过非凸支付函数的全局理性,为扩展型博弈提出了行为策略中的纳什均衡(NashEBS)概念。库恩的支付等价定理解决了非凸性问题,但它忽略了关联正规型博弈的一个纳什均衡可以对应扩展型博弈的无穷多个NashEBS。为解决这一多重性问题,迈尔森《迈尔森(1991)》中记载的传统方法涉及两步过程:先识别智能体正规型表示的纳什均衡,再验证相应的混合策略组合是否为关联正规型博弈的纳什均衡,而这一验证通常随扩展型博弈树的大小呈指数级增长。针对这些挑战,本文通过引入额外的行为策略组合和信念,提出了一种NashEBS的刻画,该刻画满足线性支付函数的局部序贯理性及自独立一致性。此刻画使得人们能够解析地确定小型扩展型博弈的所有NashEBS。基于这一刻画,我们获得了一个多项式系统,作为判断行为策略组合是否为NashEBS的充要条件。该刻画的一个应用产生了计算此类均衡的可微路径跟踪方法。
英文摘要:
The concept of Nash equilibrium in behavioral strategies (NashEBS) was formulated By Nash~\cite{Nash (1951)} for an extensive-form game through global rationality of nonconvex payoff functions. Kuhn's payoff equivalence theorem resolves the nonconvexity issue, but it overlooks that one Nash equilibrium of the associated normal-form game can correspond to infinitely many NashEBSs of an extensive-form game. To remedy this multiplicity, the traditional approach as documented in Myerson~\cite{Myerson (1991)} involves a two-step process: identifying a Nash equilibrium of the agent normal-form representation, followed by verifying whether the corresponding mixed strategy profile is a Nash equilibrium of the associated normal-form game, which often scales exponentially with the size of the extensive-form game tree. In response to these challenges, this paper develops a characterization of NashEBS through the incorporation of an extra behavioral strategy profile and beliefs, which meet local sequential rationality of linear payoff functions and self-independent consistency. This characterization allows one to analytically determine all NashEBSs for small extensive-form games. Building upon this characterization, we acquire a polynomial system serving as a necessary and sufficient condition for determining whether a behavioral strategy profile is a NashEBS. An application of the characterization yields differentiable path-following methods for computing such an equilibrium.
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。