Active learning with a misspecified prior
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 fu...
Main Authors: | Fudenberg, Drew (Contributor), Romanyuk, Gleb (Author), Strack, Philipp (Author) |
---|---|
Other Authors: | Massachusetts Institute of Technology. Department of Economics (Contributor) |
Format: | Article |
Language: | English |
Published: |
The Econometric Society,
2018-03-02T21:32:13Z.
|
Subjects: | |
Online Access: | Get fulltext |
Similar Items
-
Limit Points of Endogenous Misspecified Learning
by: Fudenberg, Drew, et al.
Published: (2022) -
The Perils of Misspecified Priors and Optional Stopping in Multi-Armed Bandits
by: Markus Loecher
Published: (2021-07-01) -
Reinforcement learning with misspecified model classes
by: Joseph, Joshua Mason, et al.
Published: (2015) -
Stochastic Restricted Biased Estimators in Misspecified Regression Model with Incomplete Prior Information
by: Manickavasagar Kayanan, et al.
Published: (2018-01-01) -
Cointegration in misspecified models
by: Pashourtidou, Nicoletta
Published: (2002)