Artikel

Equilibrium in misspecified Markov decision processes

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.

Language
Englisch

Bibliographic citation
Journal: Theoretical Economics ; ISSN: 1555-7561 ; Volume: 16 ; Year: 2021 ; Issue: 2 ; Pages: 717-757 ; New Haven, CT: The Econometric Society

Classification
Wirtschaft
Optimization Techniques; Programming Models; Dynamic Analysis
Search; Learning; Information and Knowledge; Communication; Belief; Unawareness
Subject
Misspecified model
Markov decision process
equilibrium

Event
Geistige Schöpfung
(who)
Esponda, Ignacio
Pouzo, Demian
Event
Veröffentlichung
(who)
The Econometric Society
(where)
New Haven, CT
(when)
2021

DOI
doi:10.3982/TE3843
Handle
Last update
10.03.2025, 11:44 AM CET

Data provider

This object is provided by:
ZBW - Deutsche Zentralbibliothek für Wirtschaftswissenschaften - Leibniz-Informationszentrum Wirtschaft. If you have any questions about the object, please contact the data provider.

Object type

  • Artikel

Associated

  • Esponda, Ignacio
  • Pouzo, Demian
  • The Econometric Society

Time of origin

  • 2021

Other Objects (12)