Learning in Society
AbstractIn the canonical learning model, the multi-armed bandit with independent arms, a decision maker learns about the different alternatives only through his private experience. It is well known that any optimal experimentation strategy for this problem is ex-post inefficient: it sometimes leads the superior alternative to be dropped altogether. Many situations of interest, however, involve learning from individual experience and the experience of others. This paper shows how learning in society can overcome this inefficiency. We consider an economy populated with a continuum of infinitely lived agents where each one of them faces a multi-armed bandit. The unknown stochastic payoffs of each arm are the same for all agents. In each period, they are randomly and anonymously matched in pairs, and in any such match they observe their partner's current action choice and its outcome. We establish that if initial beliefs are sufficiently heterogeneous, then the fraction of the population choosing the superior arm converges to one in any perfect bayesian equilibrium of this game. We also show that the same conclusion holds when only action choices are observable within a match and the number of arms is two
Download InfoIf you experience problems downloading a file, check if you have the proper application to view it first. In case of further problems read the IDEAS help page. Note that these files are not on the IDEAS site. Please be patient as the files may be large.
Bibliographic InfoPaper provided by Society for Economic Dynamics in its series 2006 Meeting Papers with number 435.
Date of creation: 03 Dec 2006
Date of revision:
Contact details of provider:
Postal: Society for Economic Dynamics Christian Zimmermann Economic Research Federal Reserve Bank of St. Louis PO Box 442 St. Louis MO 63166-0442 USA
Web page: http://www.EconomicDynamics.org/society.htm
More information through EDIRC
Multi-Armed Bandits; Social Learning; Strategic Experimentation;
Find related papers by JEL classification:
- C73 - Mathematical and Quantitative Methods - - Game Theory and Bargaining Theory - - - Stochastic and Dynamic Games; Evolutionary Games
- D82 - Microeconomics - - Information, Knowledge, and Uncertainty - - - Asymmetric and Private Information; Mechanism Design
- D83 - Microeconomics - - Information, Knowledge, and Uncertainty - - - Search, Learning, and Information
This paper has been announced in the following NEP Reports:
Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.:
- Godfrey Keller & Sven Rady & Martin Cripps, 2005.
"Strategic Experimentation with Exponential Bandits,"
Econometric Society, vol. 73(1), pages 39-68, 01.
- Cripps, Martin & Keller, Godfrey & Rady, Sven, 2003. "Strategic Experimentation with Exponential Bandits," Discussion Papers in Economics 4, University of Munich, Department of Economics.
- Godfrey Keller & Martin Cripps, 2003. "Strategic Experimentation with Exponential Bandits," Economics Series Working Papers 143, University of Oxford, Department of Economics.
- Cripps, Martin William & Keller, Godfrey & Rady, Sven, 2003. "Strategic Experimentation with Exponential Bandits," CEPR Discussion Papers 3814, C.E.P.R. Discussion Papers.
- Luis Araujo & Raoul Minetti, 2010. "Markets and Relationships in a Learning Economy," Review of Economic Dynamics, Elsevier for the Society for Economic Dynamics, vol. 13(3), pages 687-700, July.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Christian Zimmermann).
If references are entirely missing, you can add them using this form.