Cycling in a stochastic learning algorithm for normal form games

Martin Posch

Journal of Evolutionary Economics, 1997, vol. 7, issue 2, 193-207

Abstract: In this paper we study a stochastic learning model for 2, 2 normal form games that are played repeatedly. The main emphasis is put on the emergence of cycles. We assume that the players have neither information about the payoff matrix of their opponent nor about their own. At every round each player can only observe his or her action and the payoff he or she receives. We prove that the learning algorithm, which is modeled by an urn scheme proposed by Arthur (1993), leads with positive probability to a cycling of strategy profiles if the game has a mixed Nash equilibrium. In case there are strict Nash equilibria, the learning process converges a.s. to the set of Nash equilibria.

Keywords: Evolutionary games; Learning; Bounded rationality; Learning algorithms (search for similar items in EconPapers)
JEL-codes: C73 D83 (search for similar items in EconPapers)
Date: 1997
References: Add references at CitEc
Citations: View citations in EconPapers (33)

Downloads: (external link)
http://link.springer.de/link/service/journals/00191/papers/7007002/70070193.pdf (application/pdf)
http://link.springer.de/link/service/journals/0019 ... 07002/70070193.ps.gz (application/postscript)
Access to the full text of the articles in this series is restricted

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:spr:joevec:v:7:y:1997:i:2:p:193-207

Ordering information: This journal article can be ordered from
http://www.springer.com/economics/journal/191/PS2

Access Statistics for this article

Journal of Evolutionary Economics is currently edited by Uwe Cantner, Elias Dinopoulos, Horst Hanusch and Luigi Orsenigo

More articles in Journal of Evolutionary Economics from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().