On the convergence of reinforcement learning

• 成果类型: Article
• 署名作者: Beggs, AW
• 署名单位: University of Oxford
• 刊物名称: JOURNAL OF ECONOMIC THEORY
• ISSN/ISSBN: 0022-0531
• DOI: 10.1016/j.jet.2004.03.008
• 发表日期: 2005
• 页码: 1-36
• 关键词: Reinforcement learning; games

摘要

This paper examines the convergence of payoffs and strategies in Erev and Roth's model of reinforcement learning. When all players use this rule it eliminates iteratively dominated strategies and in two-person constant-sum games average payoffs converge to the value of the game. Strategies converge in constant-sum games with unique equilibria if they are pure or if they are mixed and the game is 2 x 2. The long-run behaviour of the learning rule is governed by equations related to Maynard Smith's version of the replicator dynamic. Properties of the learning rule against general opponents are also studied. (c) 2004 Elsevier Inc. All rights reserved.