Mean and variance responsive learning

• 成果类型: Article
• 署名作者: Oyarzun, Carlos; Sarin, Rajiv
• 署名单位: University of Birmingham; University of Queensland
• 刊物名称: GAMES AND ECONOMIC BEHAVIOR
• ISSN/ISSBN: 0899-8256
• DOI: 10.1016/j.geb.2012.02.013
• 发表日期: 2012
• 页码: 855-866
• 关键词: Learning; Reinforcement Learning; Mean and variance preferences

摘要

Decision makers are often described as seeking higher expected payoffs and avoiding higher variance in payoffs. We provide some necessary and some sufficient conditions for learning rules, that assume the agent has little prior and feedback information about the environment, to reflect such preferences. We adopt the framework of Borgers, Morales and Sarin (2004, Econometrica) who provide similar results for learning rules that seek higher expected payoffs. Our analysis reveals that a concern for variance leads to quadratic transformations of payoffs to appear in the learning rule. Crown Copyright (C) 2012 Published by Elsevier Inc. All rights reserved.