What Should Economic Agents Learn in Misspecified Environments?

11 Pages Posted: 11 Jan 2022

See all articles by Filippo Massari

Filippo Massari

Bocconi University - Department of Decision Sciences; University of East Anglia

Jonathan Newton

Kyoto University - Institute of Economic Research

Date Written: January 09, 2022

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

Suggested Citation

Massari, Filippo and Newton, Jonathan, What Should Economic Agents Learn in Misspecified Environments? (January 09, 2022). Available at SSRN: https://ssrn.com/abstract=4005854 or http://dx.doi.org/10.2139/ssrn.4005854

Filippo Massari

Bocconi University - Department of Decision Sciences ( email )

Via Roentgen 1
Milan, 20136
Italy

University of East Anglia ( email )

Norwich Research Park
Norwich, Norfolk NR4 7TJ
United Kingdom

Jonathan Newton (Contact Author)

Kyoto University - Institute of Economic Research ( email )

Yoshida-Honmachi
Sakyo-ku
Kyoto 606-8501
JAPAN

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
46
Abstract Views
166
PlumX Metrics