Wisdom of the Crowds vs. Groupthink: Learning in Groups and in Isolation

International Journal of Game Theory 42 (3):695-723 (2013)
  Copy   BIBTEX

Abstract

We evaluate the asymptotic performance of boundedly-rational strategies in multi-armed bandit problems, where performance is measured in terms of the tendency (in the limit) to play optimal actions in either (i) isolation or (ii) networks of other learners. We show that, for many strategies commonly employed in economics, psychology, and machine learning, performance in isolation and performance in networks are essentially unrelated. Our results suggest that the appropriateness of various, common boundedly-rational strategies depends crucially upon the social context (if any) in which such strategies are to be employed.

Author Profiles

David Danks
University of California, San Diego
Conor Mayo-Wilson
University of Washington

Analytics

Added to PP
2010-09-14

Downloads
719 (#18,850)

6 months
85 (#43,532)

Historical graph of downloads since first upload
This graph includes both downloads from PhilArchive and clicks on external links on PhilPapers.
How can I increase my downloads?