• *We acknowledge support of National Science Foundation Grant No. SBR-9223701 to the California Institute of Technology and the support of the JPL-Caltech supercomputer project. This was written while the second author was a visiting professor at CREST-LEI and a visiting guest at CERAS. He is grateful to both organizations for their hospitability and reseach support. a version of this paper was presented at the First Japanese Decentralization conferefnce at Keio University in November, 1994. we are grateful to the warm hospitality during that conference, and appresciate the comments received from the audience. we acknowledge valuable with Mahmoud El-Gamalk, Jacques-Franccois Thisse and Mark Fey, and the research assiatance of Eugene Grayver and Rob Weber.


This paper describes a statistical model of equiliobrium behaviour in games, which we call Quantal Response Equilibrium (QRE). The key feature of the equilibrium is that individuals do not always play responses to the strategies of their opponents, but play better strategies with higher probability than worse strategies. we illustrate several different applications of this approach, and establish a number of theoretical properties of this equilibrium concept. We also demonstrate an equililance between this equilibrium notion and Bayesian games derived from games of complete information with perturbed payoffs