Learning with perfect information

• 成果类型: Article
• 署名作者: Dubey, P; Haimanko, O
• 署名单位: Ben-Gurion University of the Negev; State University of New York (SUNY) System; Stony Brook University
• 刊物名称: GAMES AND ECONOMIC BEHAVIOR
• ISSN/ISSBN: 0899-8256
• DOI: 10.1016/S0899-8256(03)00127-1
• 发表日期: 2004
• 页码: 304-324
• 关键词: learning in extensive form games; perfect information; self-confirming and Nash equilibria; objective updates; convergence in finite time

摘要

For extensive form games with perfect information, consider a learning process in which, at any iteration, each player unilaterally deviates to a best response to his current conjectures of others' strategies; and then updates his conjectures in accordance with the induced play of the game. We show that, for generic payoffs, the outcome of the game becomes stationary, and is consistent with Nash equilibrium. In general, if payoffs have ties or if players observe more of each others' strategies than is revealed by plays of the game, the same result holds provided a rationality constraint is imposed on unilateral deviations: no player changes his moves in subgames that he deems unreachable, unless he stands to improve his payoff there. Moreover, with this constraint, the sequence of strategies and conjectures also becomes stationary, and yields a self-confirming equilibrium. (C) 2003 Elsevier Inc. All rights reserved.