2014/11/05 by Ignacio Esponda, Esponda, Ignacio, Demián Pouzo +1 · 6 citations
Decision Sciences · Social Sciences · #Computer Science and Game Theory (cs.GT) #Corruption and Economic Development #Experimental Behavioral Economics Studies #FOS: Computer and information sciences #FOS: Economics and business #Game Theory and Applications #General Economics (econ.GN)
paper · pdf · doi:10.48550/arxiv.1411.1152
openalex publication_date 2014/11/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We develop an equilibrium framework that relaxes the standard assumption that\npeople have a correctly-specified view of their environment. Each player is\ncharacterized by a (possibly misspecified) subjective model, which describes\nthe set of feasible beliefs over payoff-relevant consequences as a function of\nactions. We introduce the notion of a Berk-Nash equilibrium: Each player\nfollows a strategy that is optimal given her belief, and her belief is\nrestricted to be the best fit among the set of beliefs she considers possible.\nThe notion of best fit is formalized in terms of minimizing the\nKullback-Leibler divergence, which is endogenous and depends on the equilibrium\nstrategy profile. Standard solution concepts such as Nash equilibrium and\nself-confirming equilibrium constitute special cases where players have\ncorrectly-specified models. We provide a learning foundation for Berk-Nash\nequilibrium by extending and combining results from the statistics literature\non misspecified learning and the economics literature on learning in games.\n