Learning with Hazy Beliefs
AbstractPlayers are rational if they always choose best replies given their beliefs. They are good predictors if the difference between their beliefs and the distribution of the others' actual strategies goes to zero over time. Learning is deterministic if beliefs are fully determined by the initial conditions and the observed data. (Bayesian updating is a particular example). If players are rational, good predictors, and learn deterministically, there are many games for which neither beliefs nor actions converge to a Nash equilibrium. We introduce an alternative approach to learning called prospecting in which players are rational and good predictors, but beliefs have a small random component. In any finite game, and from any initial conditions, prospecting players learn to play arbitrarily close to Nash equilibrium with probability one.
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 ESRC Centre on Economics Learning and Social Evolution in its series ELSE working papers with number 023.
Date of creation:
Date of revision:
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.:
- J. Jordan, 2010. "Three Problems in Learning Mixed-Strategy Equilibria," Levine's Working Paper Archive 475, David K. Levine.
- Foster, Dean P. & Vohra, Rakesh V., 1997. "Calibrated Learning and Correlated Equilibrium," Games and Economic Behavior, Elsevier, vol. 21(1-2), pages 40-55, October.
- Drew Fudenberg & David Kreps, 2010.
"Learning Mixed Equilibria,"
Levine's Working Paper Archive
415, David K. Levine.
- Nyarko, Yaw, 1994. "Bayesian Learning Leads to Correlated Equilibria in Normal Form Games," Economic Theory, Springer, vol. 4(6), pages 821-41, October.
- Turdaliev, Nurlan, 2002. "Calibration and Bayesian learning," Games and Economic Behavior, Elsevier, vol. 41(1), pages 103-119, October.
- Eric Friedman, 1998. "Learnability of a class of Non-atomic Games arising on the Internet," Departmental Working Papers 199824, Rutgers University, Department of Economics.
- Matthew O. Jackson & Ehud Kalai, 1997.
"False Reputation in a Society of Players,"
Game Theory and Information
- Foster, Dean P. & Young, H. Peyton, 2003.
"Learning, hypothesis testing, and Nash equilibrium,"
Games and Economic Behavior,
Elsevier, vol. 45(1), pages 73-96, October.
- Timothy Salmon, 2004. "Evidence for Learning to Learn Behavior in Normal Form Games," Theory and Decision, Springer, vol. 56(4), pages 367-404, 04.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (s. malkani) The email address of this maintainer does not seem to be valid anymore. Please ask s. malkani to update the entry or send us the correct address.
If references are entirely missing, you can add them using this form.