A Behavioral Learning Process in Games

Jean-François Laslier, R. Topol and Bernard Walliser

Working Papers from Paris X - Nanterre, U.F.R. de Sc. Ec. Gest. Maths Infor.

Abstract: The paper studies a behavioral learning process where an agent plays, at each period, an action with a probability which is proportional to the cumulative utility he got in the past with that action. The so-called CPR learning rule and the dynamic process it induces are formally stated and compared to other reinforcement rules as well as to fictitious play or the replicator dynamics.

Keywords: LEARNING; GAME THEORY; BEHAVIOUR (search for similar items in EconPapers)
JEL-codes: C70 D83 (search for similar items in EconPapers)
Pages: 34 pages
Date: 1999
References: Add references at CitEc
Citations: View citations in EconPapers (4)

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
Journal Article: A Behavioral Learning Process in Games (2001)
Working Paper: A behavioral learning process in games (1999)
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:fth:pnegmi:99-03

Access Statistics for this paper

More papers in Working Papers from Paris X - Nanterre, U.F.R. de Sc. Ec. Gest. Maths Infor. THEMA, Universite de Paris X-Nanterre, U.F.R. de science economiques, gestion, mathematiques et informatique, 200, avenue de la Republique 92001 Nanterre CEDEX..
Bibliographic data for series maintained by Thomas Krichel ().