Learning, Matching and Aggregation

Ed Hopkins

Game Theory and Information from University Library of Munich, Germany

Abstract: Fictitious play and ``gradient'' learning are examined in the context of a large population where agents are repeatedly randomly matched. We show that the aggregation of this learning behaviour can be qualitatively different from learning at the level of the individual. This aggregate dynamic belongs to the same class of simply defined dynamic as do several formulations of evolutionary dynamics. We obtain sufficient conditions for convergence and divergence which are valid for the whole class of dynamics. These results are therefore robust to most specifications of adaptive behaviour.

JEL-codes: C72 D83 (search for similar items in EconPapers)
Pages: 34 pages
Date: 1995-12-05
Note: Latex file, 34 pages including 2 figures.
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (3)

Downloads: (external link)
https://econwpa.ub.uni-muenchen.de/econ-wp/game/papers/9512/9512001.tex (application/x-tex)
https://econwpa.ub.uni-muenchen.de/econ-wp/game/papers/9512/9512001.pdf (application/pdf)
https://econwpa.ub.uni-muenchen.de/econ-wp/game/papers/9512/9512001.ps.gz (application/postscript)

Related works:
Journal Article: Learning, Matching, and Aggregation (1999)
Working Paper: Learning, Matching and Aggregation (1995)
Working Paper: Learning, Matching and Aggregation (1995)
Working Paper: Learning, Matching and Aggregation
Working Paper: Learning, Matching and Aggregation
Working Paper: Learning, Matching and Aggregation
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:wpa:wuwpga:9512001

Access Statistics for this paper

More papers in Game Theory and Information from University Library of Munich, Germany
Bibliographic data for series maintained by EconWPA ( this e-mail address is bad, please contact ).