The possibility of Bayesian learning in repeated games

• 成果类型: Article
• 署名作者: Norman, Thomas W. L.
• 署名单位: University of Oxford
• 刊物名称: GAMES AND ECONOMIC BEHAVIOR
• ISSN/ISSBN: 0899-8256
• DOI: 10.1016/j.geb.2022.09.002
• 发表日期: 2022
• 页码: 142-152
• 关键词: Repeated games; Nash equilibrium; Bayesian learning; Rational learning; Consistency

摘要

In infinitely repeated games, Nachbar (1997, 2005) has shown that Bayesian learning of a restricted strategy set is inconsistent; the beliefs required to learn any element of such a set will lead best responses to lie outside of it in most games. But I establish here that Nash convergence of Bayesian learning requires only that optimal play (rather than any possible play) is learnable, and an appropriately modified notion of learnability is consistent in many of the games to which Nachbar's result applies. This means that rational learning of equilibrium is possible in an important class including coordination games, which I illustrate with two examples of positive learning results.(c) 2022 The Author(s). Published by Elsevier Inc. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).