Learning, Matching and Aggregation

Research output: Working paperDiscussion paper

Abstract / Description of output

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 di�erent from learning at the level of the individual. This aggregate dynamic belongs to the same class of simply de
Original languageEnglish
PublisherESRC Centre on Economics Learning and Social Evolution
Publication statusPublished - 1996

Publication series

NameELSE working papers


Dive into the research topics of 'Learning, Matching and Aggregation'. Together they form a unique fingerprint.

Cite this