Equilibrium in misspecified Markov decision processes

Ignacio Esponda and Demian Pouzo ()
Additional contact information
Demian Pouzo: Department of Economics, UC Berkeley

Theoretical Economics, 2021, vol. 16, issue 2

Abstract: We provide an equilibrium framework for modeling the behavior of an agent who holds a simplified view of a dynamic optimization problem. The agent faces a Markov Decision Process, where a transition probability function determines the evolution of a state variable as a function of the previous state and the agent’s action. The agent is uncertain about the true transition function and has a prior over a set of possible transition functions; this set reflects the agent’s (possibly simplified) view of her environment and may not contain the true function. We define an equilibrium concept and provide conditions under which it characterizes steady-state behavior when the agent updates her beliefs using Bayes’ rule.

Keywords: Misspecified model; Markov decision process; equilibrium (search for similar items in EconPapers)
JEL-codes: C61 D83 (search for similar items in EconPapers)
Date: 2021-05-03
References: View complete reference list from CitEc
Citations: View citations in EconPapers (4)

Downloads: (external link)
http://econtheory.org/ojs/index.php/te/article/viewFile/20210717/30649/886 (application/pdf)

Related works:
Working Paper: Equilibrium in Misspecified Markov Decision Processes (2016)
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:3843

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 ().