BAYESIAN LEARNING, SMOOTH APPROXIMATE OPTIMAL BEHAVIOR, AND CONVERGENCE TO ε-NASH EQUILIBRIUM

• 成果类型: Article
• 署名作者: Noguchi, Yuichi
• 署名单位: Kanto Gakuin University
• 刊物名称: ECONOMETRICA
• ISSN/ISSBN: 0012-9682
• DOI: 10.3982/ECTA9332
• 发表日期: 2015
• 页码: 353-373
• 关键词: Repeated games; incomplete information; hypothesis

摘要

In this paper, I construct players' prior beliefs and show that these prior beliefs lead the players to learn to play an approximate Nash equilibrium uniformly in any infinitely repeated slightly perturbed game with discounting and perfect monitoring. That is, given any epsilon > 0, there exists a (single) profile of players' prior beliefs that leads play to almost surely converge to an epsilon-Nash equilibrium uniformly for any (finite normal form) stage game with slight payoff perturbation and any discount factor less than 1.