This file is part of IDEAS, which uses RePEc data


[ Papers | Articles | Software | Books | Chapters | Authors | Institutions | JEL Classification | NEP reports | Search | New papers by email | Author registration | Rankings | Volunteers | FAQ | Blog | Help! ]

Learning to Play Nash in Deterministic Uncoupled Dynamics

Author info | Abstract | Publisher info | Download info | Related research | Statistics
Author Info
Vivaldo M. Mendes () (ISCTE - Department of Economics and UNIDE-ERC)
Diana A. Mendes () (ISCTE - Department of Quantitative Methods and UNIDE-StatMath)
Orlando Gomes () (Instituto Politécnico de Lisboa - Escola Superior de Comunicação Social and UNIDE-ERC)

Additional information is available for the following registered author(s):

Abstract

This paper is concerned with the following problem. In a bounded rational game where players cannot be as super-rational as in Kalai and Leher (1993), are there simple adaptive heuristics or rules that can be used in order to secure convergence to Nash equilibria, or convergence only to a larger set designated by correlated equilibria? Are there games with uncoupled deterministic dynamics in discrete time that converge to Nash equilibrium or not? Young (2008) argues that if an adaptive learning rule follows three conditions – (i) it is uncoupled, (ii) each player’s choice of action depends solely on the frequency distribution of past play, and (iii) each player’s choice of action, conditional on the state, is deterministic – no such rule leads the players’ behavior to converge to Nash equilibrium. In this paper we present a counterexample, showing that there are simple adaptive rules that secure convergence, in fact fast convergence, in a fully deterministic and uncoupled game. We used the Cournot model with nonlinear costs and incomplete information for this purpose and also illustrate that this convergence can be achieved with or without any coordination of the players actions.

Download Info
To download:

If you experience problems downloading a file, check if you have the proper application to view it first. Information about this may be contained in the File-Format links below. 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.

File URL: http://erc.unide.iscte.pt/wpi/ERCwp1808.pdf
File Format: application/pdf
File Function: First version, 2008
Download Restriction: no

Publisher Info
Paper provided by ISCTE, UNIDE, Economics Research Centre in its series Working Papers with number ercwp1808.

Download reference. The following formats are available: HTML (with abstract), plain text (with abstract), BibTeX, RIS (EndNote, RefMan, ProCite), ReDIF
Length: 31 pages
Date of creation: 2008
Date of revision:
Handle: RePEc:isc:wpaper:ercwp1808

Contact details of provider:
Email:
Web page: http://erc.unide.iscte.pt
More information through EDIRC

For technical questions regarding this item, or to correct its listing, contact: (Henrique Monteiro) The email address of this maintainer does not seem to be valid anymore. Please ask Henrique Monteiro to update the entry or send us the correct address..

Related research
Keywords: Uncoupled Deterministic Dynamics; Nash Equilibrium; Bounded Learning; Convergence.;

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.:

  1. Germano, Fabrizio & Lugosi, Gabor, 2007. "Global Nash convergence of Foster and Young's regret testing," Games and Economic Behavior, Elsevier, vol. 60(1), pages 135-154, July. [Downloadable!] (restricted)
    Other versions:
  2. Foster, Dean P. & Young, H. Peyton, 2006. "Regret testing: learning to play Nash equilibrium without knowing you have an opponent," Theoretical Economics, Society for Economic Theory, vol. 1(3), pages 341-367, September. [Downloadable!]
  3. 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. [Downloadable!] (restricted)
  4. Sergiu Hart & Andreu Mas-Colell, 2000. "A Simple Adaptive Procedure Leading to Correlated Equilibrium," Econometrica, Econometric Society, vol. 68(5), pages 1127-1150, September.
    Other versions:
  5. Foster, Dean P. & Vohra, Rakesh, 1999. "Regret in the On-Line Decision Problem," Games and Economic Behavior, Elsevier, vol. 29(1-2), pages 7-35, October. [Downloadable!] (restricted)
  6. Kalai, Ehud & Lehrer, Ehud, 1993. "Rational Learning Leads to Nash Equilibrium," Econometrica, Econometric Society, vol. 61(5), pages 1019-45, September. [Downloadable!] (restricted)
    Other versions:
  7. Cox, James C. & Walker, Mark, 1998. "Learning to play Cournot duopoly strategies," Journal of Economic Behavior & Organization, Elsevier, vol. 36(2), pages 141-161, August. [Downloadable!] (restricted)
  8. Leslie, David S. & Collins, E.J., 2006. "Generalised weakened fictitious play," Games and Economic Behavior, Elsevier, vol. 56(2), pages 285-298, August. [Downloadable!] (restricted)
  9. Sergiu Hart & Andreu Mas-Colell, 2003. "Uncoupled Dynamics Do Not Lead to Nash Equilibrium," American Economic Review, American Economic Association, vol. 93(5), pages 1830-1836, December. [Downloadable!]
Full references

Statistics
Access and download statistics

Did you know? To receive notification of recent additions to the database, subscribe to the free NEP reports.

This page was last updated on 2009-11-26.


This information is provided to you by IDEAS at the Department of Economics, College of Liberal Arts and Sciences, University of Connecticut using RePEc data on a server sponsored by the Society for Economic Dynamics.