Active learning with a misspecified prior
Name
Fudenberg_et_al-2017-Theoretical_Economics.pdf
Size
366.47 KB
Format
Adobe PDF
Checksum (MD5)
37f3f3058d1b703f19041239cd34ec35
Author(s)
Fudenberg, Drew
Romanyuk, Gleb
Strack, Philipp
Date Issued
September 2017
Journal
Theoretical Economics
Publisher
The Econometric Society
Citation
Fudenberg, Drew, Gleb Romanyuk, and Philipp Strack. “Active Learning with a Misspecified Prior.” Theoretical Economics 12, no. 3 (September 2017): 1155–1189.
Version
Final published version
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.
MIT Department
Massachusetts Institute of Technology. Department of Economics
Terms of Use
Creative Commons Attribution-NonCommercial 4.0 International
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.3982/TE2480
