The dynamics of generalized reinforcement learning

• 成果类型: Article
• 署名作者: Lahkar, Ratul; Seymour, Robert M.
• 署名单位: KREA University; IFMR - Graduate School of Business (GSB); University of London; University College London
• 刊物名称: JOURNAL OF ECONOMIC THEORY
• ISSN/ISSBN: 0022-0531
• DOI: 10.1016/j.jet.2014.01.002
• 发表日期: 2014
• 页码: 584-595
• 关键词: Reinforcement learning; Negative reinforcement; Replicator dynamic

摘要

We consider reinforcement learning in games with both positive and negative payoffs. The Cross rule is the prototypical reinforcement learning rule in games that have only positive payoffs. We extend this rule to incorporate negative payoffs to obtain the generalized reinforcement learning rule. Applying this rule to a population game, we obtain the generalized reinforcement dynamic which describes the evolution of mixed strategies in the population. We apply the dynamic to the class of Rock Scissor Paper (RSP) games to establish local convergence to the interior rest point in all such games, including the bad RSP game. (C) 2014 Elsevier Inc. All rights reserved.