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! ]

Stochastic approximation, Momentum, and Nash play

Author info | Abstract | Publisher info | Download info | Related research | Statistics
Author Info
Berglann, Helge ()
Flåm, Sjur () (Department of Economics, University of Bergen.)

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

Abstract

Main objects here are normal-form games, featuring uncertainty and noncooperative players who entertain local visions, form local approximations, and hesitate in making large, swift adjustments. For the purpose of reaching Nash equilibrium, or learning such play, we advocate and illustrate an algorithm that combines stochastic gradient projection with the heavyball method. What emerges is a coupled, constrained, second-order stochastic process. Some friction feeds into and stabilizes myopic approximations. Convergence to Nash play obtains under seemingly weak and natural conditions, an important one being that accumulated marginal payoffs remains bounded above.

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: ftp://ftp.uib.no/pub/econ/wp/wp0209.pdf
File Format: application/pdf
File Function:
Download Restriction: no

Publisher Info
Paper provided by Department of Economics, University of Bergen in its series Working paper Series with number 0209.

Download reference. The following formats are available: HTML (with abstract), plain text (with abstract), BibTeX, RIS (EndNote, RefMan, ProCite), ReDIF
Length: 9 pages
Date of creation: 03 Apr 2002
Date of revision:
Handle: RePEc:uib:bereco:0209

Contact details of provider:
Postal: Fosswinckelsgate 14, N-5007 Bergen
Phone: (+47)55589200
Fax: (+47)55589210
Email:
Web page: http://www.uib.no/econ/
More information through EDIRC

For technical questions regarding this item, or to correct its listing, contact: (Bjørn Sandvik).

Related research
Keywords: Noncooperative games; Nash equilibrium; stochastic programming and approximation; the heavy ball method.;

Find related papers by JEL classification:
C63 - Mathematical and Quantitative Methods - - Mathematical Methods and Programming - - - Computational Techniques
C72 - Mathematical and Quantitative Methods - - Game Theory and Bargaining Theory - - - Noncooperative Games
C73 - Mathematical and Quantitative Methods - - Game Theory and Bargaining Theory - - - Stochastic and Dynamic Games; Evolutionary Games

This paper has been announced in the following NEP Reports:

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. Fudenberg, Drew & Levine, David, 1998. "Learning in games," European Economic Review, Elsevier, vol. 42(3-5), pages 631-639, May. [Downloadable!] (restricted)
  2. Jacob K. Goeree & Charles A. Holt, 2001. "Ten Little Treasures of Game Theory and Ten Intuitive Contradictions," American Economic Review, American Economic Association, vol. 91(5), pages 1402-1422, December. [Downloadable!] (restricted)
    Other versions:
  3. Flam, S.D., 1999. "Learning Equilibrium Play: a Myopic Approach," Norway; Department of Economics, University of Bergen 189, Department of Economics, University of Bergen.
  4. Flam, Sjur Didrik, 1996. "Approaches to economic equilibrium," Journal of Economic Dynamics and Control, Elsevier, vol. 20(9-10), pages 1505-1522. [Downloadable!] (restricted)
  5. Flam, S.D., 2001. "Approaching Equilibrium in Parallel," Norway; Department of Economics, University of Bergen 0601, Department of Economics, University of Bergen.
    Other versions:
Full references

Statistics
Access and download statistics

Did you know? You too can volunteer for RePEc, for example by providing information about publications in your institution.

This page was last updated on 2010-1-28.

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.