Active learning with a misspecified prior

Drew Fudenberg, Gleb Romanyuk () and Philipp Strack ()
Additional contact information
Gleb Romanyuk: Department of Economics, Harvard University

Theoretical Economics, 2017, vol. 12, issue 3

Abstract: We study learning and information acquisition by a Bayesian agent whose prior belief is misspecified in the sense that it assigns probability zero to the true state of the world. At each instant, the agent takes an action and observes the corresponding payoff, which is the sum of a fixed but unknown function of the action and an additive error term. We provide a complete characterization of asymptotic actions and beliefs when the agent's subjective state space is a doubleton. A simple example with three actions shows that in a misspecified environment a myopic agent's beliefs converge while a sufficiently patient agent's beliefs do not. This illustrates a novel interaction between misspecification and the agent's subjective discount rate.

Keywords: Active learning; learning in games; mis-specified models (search for similar items in EconPapers)
JEL-codes: D83 D90 (search for similar items in EconPapers)
Date: 2017-09-26
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (44)

Downloads: (external link)
http://econtheory.org/ojs/index.php/te/article/viewFile/20171155/18844/562 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:the:publsh:2480

Access Statistics for this article

Theoretical Economics is currently edited by Simon Board, Todd D. Sarver, Juuso Toikka, Rakesh Vohra, Pierre-Olivier Weill

More articles in Theoretical Economics from Econometric Society
Bibliographic data for series maintained by Martin J. Osborne ().