A note on absolutely expedient learning rules

• 成果类型: Article
• 署名作者: Oyarzun, Carlos
• 署名单位: University of Queensland
• 刊物名称: JOURNAL OF ECONOMIC THEORY
• ISSN/ISSBN: 0022-0531
• DOI: 10.1016/j.jet.2014.07.002
• 发表日期: 2014
• 页码: 213-223
• 关键词: Absolute expediency; Learning rules; Built-in similarity

摘要

I provide a full characterization of the set of absolutely expedient learning rules introduced in Borgers et al. [2]. The expected change in the expected payoff can be written as a quadratic form on the vector of relative expected payoffs of the strategies. This permits use of standard linear algebra arguments to provide a characterization in terms of the matrix defining this quadratic form. (C) 2014 Elsevier Inc. All rights reserved.