Convergence of least squares learning in self-referential discontinuous stochastic models

• 成果类型: Article
• 署名作者: Cho, IK
• 署名单位: University of Illinois System; University of Illinois Urbana-Champaign
• 刊物名称: JOURNAL OF ECONOMIC THEORY
• ISSN/ISSBN: 0022-0531
• DOI: 10.1006/jeth.2001.2791
• 发表日期: 2001
• 页码: 78-114
• 关键词: discontinuous decision rule; rational expectations; recursive learning; search; stochastic approximation

摘要

We examine the stability of rational expectations equilibria in the class of models in which the decision of the individual agent is discontinuous with respect to the state variables. Instead of rational expectations, each agent learns the unknown parameters through a recursive Stochastic algorithm. If the agents update the estimated value function rapidly enough, then each agent learns the true value function associated with the optimal action with prohability 1 and almost always takes the optimal action asymptotically. (C), 2001 Academic Press.