Why Imitate, and If So, How?: A Boundedly Rational Approach to Multi-armed Bandits

Individuals in a finite population repeatedly choose among actions yielding uncertain payoffs. Between choices, each individual observes the action and realized outcome ofoneother individual. We restrict our search to learning rules with limited memory that increase expected payoffs regardless of th...

Full description

Saved in:
Bibliographic Details
Published in:Journal of economic theory 1998-01, Vol.78 (1), p.130-156
Main Author: Schlag, Karl H.
Format: Article
Language:English
Subjects:
Decision
Decision making
Decision theory
Economic behaviour
Economic theory
Innovation
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Individuals in a finite population repeatedly choose among actions yielding uncertain payoffs. Between choices, each individual observes the action and realized outcome ofoneother individual. We restrict our search to learning rules with limited memory that increase expected payoffs regardless of the distribution underlying their realizations. It is shown that the rule that outperforms all others is that which imitates the action of an observed individual (whose realized outcome is better than self) with a probability proportional to the difference in these realizations. When each individual uses this best rule, the aggregate population behavior is approximated by the replicator dynamic.Journal of Economic LiteratureClassification Numbers: C72, C79, D83.
ISSN:0022-0531
1095-7235
DOI:10.1006/jeth.1997.2347