• Table of Contents
    • Abstract
    • Keywords
    • Article
      • 1 Introduction
      • 2 EWA learning
      • 3 Reinforcement learning
      • 4 Belief learning
      • 5 A graphical representation
      • 6 Linking learning and equilibrium models
      • 7 Conclusions and future research
    • See Also
    • Bibliography
    • How to cite this article

individual learning in games

Teck H. Ho
From The New Palgrave Dictionary of Economics, Second Edition, 2008
Edited by Steven N. Durlauf and Lawrence E. Blume
Back to top

Abstract

This article reviews individual models of learning in games. We show that the experience-weighted attraction (EWA) learning nests different forms of reinforcement and belief learning, and that belief learning is mathematically equivalent to generalized reinforcement, where even unchosen strategies are reinforced. Many studies consisting of thousands of observations suggest that the EWA model predicts behaviour out-of-sample better than its special cases. We also describe a generalization of EWA learning to investigate anticipation by some players that others are learning. This generalized framework links equilibrium and learning models, and improves predictive performance when players are experienced and sophisticated.
Back to top

Keywords

Back to top

Article

Back to top

How to cite this article

Ho, Teck H. "individual learning in games." The New Palgrave Dictionary of Economics. Second Edition. Eds. Steven N. Durlauf and Lawrence E. Blume. Palgrave Macmillan, 2008. The New Palgrave Dictionary of Economics Online. Palgrave Macmillan. 27 August 2014 <http://www.dictionaryofeconomics.com/article?id=pde2008_L000055> doi:10.1057/9780230226203.0780

Download Citation:

as RIS | as text | as CSV | as BibTex