Learning in Society
In 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
|Date of creation:||03 Dec 2006|
|Contact details of provider:|| Postal: Society for Economic Dynamics Marina Azzimonti Department of Economics Stonybrook University 10 Nicolls Road Stonybrook NY 11790 USA|
Web page: http://www.EconomicDynamics.org/
More information through EDIRC
References listed on IDEAS
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.:
- Abhijit Banerjee & Drew Fudenberg, 2010.
"Word of Mouth Learning,"
Levine's Working Paper Archive
723, David K. Levine.
- James Peck & Huanxing Yang, 2011. "Investment Cycles, Strategic Delay, And Self‐Reversing Cascades," International Economic Review, Department of Economics, University of Pennsylvania and Osaka University Institute of Social and Economic Research Association, vol. 52(1), pages 259-280, 02.
- Godfrey Keller & Sven Rady & Martin Cripps, 2005.
"Strategic Experimentation with Exponential Bandits,"
Econometric Society, vol. 73(1), pages 39-68, 01.
- Cripps, Martin William & Keller, R Godfrey & Rady, Sven, 2003. "Strategic Experimentation with Exponential Bandits," CEPR Discussion Papers 3814, C.E.P.R. Discussion Papers.
- Cripps, Martin & Keller, Godfrey & Rady, Sven, 2003. "Strategic Experimentation with Exponential Bandits," Discussion Papers in Economics 4, University of Munich, Department of Economics.
- A. Banerjee & Drew Fudenberg, 2010.
"Word-of-Mouth Communication and Social Learning,"
Levine's Working Paper Archive
425, David K. Levine.
- Konrad Podczeck & Daniela Puzzello, 2012.
"Independent random matching,"
Springer;Society for the Advancement of Economic Theory (SAET), vol. 50(1), pages 1-29, May.
- Dennis E. Smallwood & John Conlisk, 1979. "Product Quality in Markets Where Consumers are Imperfectly Informed," The Quarterly Journal of Economics, Oxford University Press, vol. 93(1), pages 1-23.
- Banks, J.s. & Sunderam, R.K., 1991.
RCER Working Papers
277, University of Rochester - Center for Economic Research (RCER).
- Dinah Rosenberg & Eilon Solan & Nicolas Vieille, 2004.
"Social Learning in One-Arm Bandit Problems,"
1396, Northwestern University, Center for Mathematical Studies in Economics and Management Science.
- Smith, L. & Sorensen, P., 1996.
"Pathological Outcomes of Observational Learning,"
96-19, Massachusetts Institute of Technology (MIT), Department of Economics.
- Ellison, Glenn & Fudenberg, Drew, 1993.
"Rules of Thumb for Social Learning,"
3196332, Harvard University Department of Economics.
- Allison, G. & Fudenberg, D., 1992. "Rules of Thumb for Social Learning," Working papers 92-12, Massachusetts Institute of Technology (MIT), Department of Economics.
- G. Ellison & D. Fudenberg, 2010. "Rules of Thumb for Social Learning," Levine's Working Paper Archive 435, David K. Levine.
- Ellison, Glenn & Fudenberg, Drew, 1992. "Rules of Thumb for Social Learning," IDEI Working Papers 17, Institut d'Économie Industrielle (IDEI), Toulouse.
- Caplin, Andrew & Leahy, John, 1994.
"Business as Usual, Market Crashes, and Wisdom after the Fact,"
American Economic Review,
American Economic Association, vol. 84(3), pages 548-565, June.
- Caplin, A. & Leahy, J., 1992. "Business as Usual, Market Crashes, and Wisdom after the Fact," Harvard Institute of Economic Research Working Papers 1594, Harvard - Institute of Economic Research.
- Rosenberg, Dinah & Solan, Eilon & Vieille, Nicolas, 2009.
"Informational externalities and emergence of consensus,"
Games and Economic Behavior,
Elsevier, vol. 66(2), pages 979-994, July.
- Nicolas Vieille & Eilon Solan & Dinah Rosenberg, 2009. "Informational externalities and emergence of consensus," Post-Print hal-00464565, HAL.
- Chamley, Christophe & Gale, Douglas, 1994.
"Information Revelation and Strategic Delay in a Model of Investment,"
Econometric Society, vol. 62(5), pages 1065-1085, September.
- Gale, D. & Chamley, C., 1992. "Information Revelation and Strategic Delay in a Model of Investment," Papers 10, Boston University - Department of Economics.
- Juang, Wei-Torng, 2001. "Learning from Popularity," Econometrica, Econometric Society, vol. 69(3), pages 735-747, May.
- Venkatesh Bala & Sanjeev Goyal, 1998. "Learning from Neighbours," Review of Economic Studies, Oxford University Press, vol. 65(3), pages 595-621.
- Sushil Bikhchandani & David Hirshleifer & Ivo Welch, 2010.
"A theory of Fads, Fashion, Custom and cultural change as informational Cascades,"
Levine's Working Paper Archive
1193, David K. Levine.
- Bikhchandani, Sushil & Hirshleifer, David & Welch, Ivo, 1992. "A Theory of Fads, Fashion, Custom, and Cultural Change in Informational Cascades," Journal of Political Economy, University of Chicago Press, vol. 100(5), pages 992-1026, October.
- Aoyagi, Masaki, 1998. "Mutual Observability and the Convergence of Actions in a Multi-Person Two-Armed Bandit Model," Journal of Economic Theory, Elsevier, vol. 82(2), pages 405-424, October.
- Monica Brezzi & Tze Leung Lai, 2000. "Incomplete Learning from Endogenous Data in Dynamic Allocation," Econometrica, Econometric Society, vol. 68(6), pages 1511-1516, November.
- Crimaldi, Irene & Pratelli, Luca, 2005. "Two inequalities for conditional expectations and convergence results for filters," Statistics & Probability Letters, Elsevier, vol. 74(2), pages 151-162, September.
- Easley, David & Kiefer, Nicholas M, 1988. "Controlling a Stochastic Process with Unknown Parameters," Econometrica, Econometric Society, vol. 56(5), pages 1045-1064, September.
- Gale, Douglas & Kariv, Shachar, 2003. "Bayesian learning in social networks," Games and Economic Behavior, Elsevier, vol. 45(2), pages 329-346, November.
- Abhijit V. Banerjee, 1992. "A Simple Model of Herd Behavior," The Quarterly Journal of Economics, Oxford University Press, vol. 107(3), pages 797-817.
- Rothschild, Michael, 1974. "A two-armed bandit theory of market pricing," Journal of Economic Theory, Elsevier, vol. 9(2), pages 185-202, October.
- Patrick Bolton & Christopher Harris, 1999. "Strategic Experimentation," Econometrica, Econometric Society, vol. 67(2), pages 349-374, March.
When requesting a correction, please mention this item's handle: RePEc:red:sed006:435. See general information about how to correct material in RePEc.
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.