Why Imitate, and if so, How? A Bounded Rational Approach to Multi- Armed Bandits

Karl H. Schlag ()

ELSE working papers from ESRC Centre on Economics Learning and Social Evolution

Abstract: We consider the situation in which individuals in a finite population must repeatedly choose an action yielding an uncertain payoff. Between choices, each individual may observe the performance of one other individual. We search for rules of behavior with limited memory that increase expected pay-off s for any underlying payoff distribution. It is shown that the rule that outperforms all other rules with this property is the one that specifies imita-tion of the action of an individual that performed better with a probability proportional to how much better she performed. When each individual uses this best rule, the aggregate population behavior can be approximated by the replicator dynamic.

Keywords: social learning; bounded rationality; imitation; multi-armed bandit; random matching; payoff increasing; replicator dynamic. (search for similar items in EconPapers)
JEL-codes: C72 C79 (search for similar items in EconPapers)
View list of references View citations in EconPapers

Downloads: (external link)
ftp://all.repec.org/RePEc/els/esrcls/ken361.pdf (application/pdf)

Related works:
Working Paper: Why Imitate, and if so, How? A Bounded Rational Approach to Multi-Armed Bandits (1996)
Journal Article: Why Imitate, and If So, How?,: A Boundedly Rational Approach to Multi-armed Bandits (1998)
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: http://EconPapers.repec.org/RePEc:els:esrcls:028

Access Statistics for this paper

More papers in ELSE working papers from ESRC Centre on Economics Learning and Social Evolution
Contact information at EDIRC.
Series data maintained by s. malkani ().