What Should Economic Agents Learn in Misspecified Environments?

Abstract

In misspecified environments, should an economic agent act rationally towards optimizing some goal? If so, what should that goal be? Prior work has focused on the goal of bidirectional consistency of beliefs and actions, in effect finding a Nash equilibrium of an imaginary game in which one player chooses actions and another player chooses beliefs. In general, such outcomes maximize neither log-likelihood nor objective payoffs over the combined space of beliefs and actions. We suggest a goal and associated learning algorithm to maximize these latter quantities.

Keywords: misspecified learning, evolutionary models.

JEL Classification: C7, D8