Please use this identifier to cite or link to this item: http://hdl.handle.net/10419/197130
Authors: 
Fudenberg, Drew
Romanyuk, Gleb
Strack, Philipp
Year of Publication: 
2017
Citation: 
[Journal:] Theoretical Economics [ISSN:] 1555-7561 [Volume:] 12 [Year:] 2017 [Issue:] 3 [Pages:] 1155-1189
Abstract: 
We study learning and information acquisition by a Bayesian agent whose prior belief is misspecified in the sense that it assigns probability 0 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.
Subjects: 
Active learning
learning in games
misspecified models
JEL: 
D83
D90
Persistent Identifier of the first edition: 
Creative Commons License: 
https://creativecommons.org/licenses/by-nc/4.0/
Document Type: 
Article

Files in This Item:
File
Size
366.47 kB





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.