Models of learning in games: An overview
G. Chernov and
I. Susin
Additional contact information
G. Chernov: HSE laboratory for experimental and behavioral economics, Moscow, Russia
I. Susin: HSE laboratory for experimental and behavioral economics, Moscow, Russia
Journal of the New Economic Association, 2019, vol. 44, issue 4, 77-125
Abstract:
This survey analyzes central ideas and the current state of the economic theory of learning in games. In game theory learning can be thought of as both an alternative to equilibria and as a way to better understand the nature of equilibria. Outside of game theory, theory of learning shows economic theory (for example, the classic Cournot oligopoly) in a new light, provides interesting theoretical problems, is nontrivial from econometric perspective. It can be studied with experimental methods. It also links economics to unexpected scientific disciplines: biology, philosophy of rationality and computer science. However, existing surveys are not particularly accessible to beginners and are not accessible at all in Russian. This survey intends to fill these gaps. It can serve both as an introduction and as a short reference. We analyze issues of classification as well as the models themselves. Theoretical descriptions are illustrated with concrete examples. Special attention is devoted to the empirical and experimental work. We also draw conclusions and hypothesize on perspectives of the field and its future role in economic theory.
Keywords: reinforcement learning; fictitious play; rational learning; bounded rationality; models of learning (search for similar items in EconPapers)
JEL-codes: C70 D84 (search for similar items in EconPapers)
Date: 2019
References: View references in EconPapers View complete reference list from CitEc
Citations:
Downloads: (external link)
http://www.econorus.org/repec/journl/2019-44-77-125r.pdf (application/pdf)
Related works:
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:nea:journl:y:2019:i:44:p:77-125
DOI: 10.31737/2221-2264-2019-44-4-3
Access Statistics for this article
Journal of the New Economic Association is currently edited by Victor Polterovich and Aleksandr Rubinshtein
More articles in Journal of the New Economic Association from New Economic Association Contact information at EDIRC.
Bibliographic data for series maintained by Alexey Tcharykov ().