Strategy Learning in 3x3 Games by Neural Networks
AbstractThis paper presents a neural network based methodology for examining the learning of game-playing rules in never-before seen games. A network is trained to pick Nash equilibria in a set of games and then released to play a larger set of new games. While faultlessly selecting Nash equilibria in never-before seen games is too complex a task for the network, Nash equilibria are chosen approximately 60% of the times. Furthermore, despite training the network to select Nash equilibria, what emerges are endogenously obtained bounded-rational rules which are closer to payoff dominance, and the best response to payoff dominance.
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 Faculty of Economics, University of Cambridge in its series Cambridge Working Papers in Economics with number 0207.
Date of creation: Mar 2002
Date of revision:
Contact details of provider:
Web page: http://www.econ.cam.ac.uk/index.htm
rationality; learning; neural networks; normal form games; complexity;
Find related papers by JEL classification:
- C72 - Mathematical and Quantitative Methods - - Game Theory and Bargaining Theory - - - Noncooperative Games
- D00 - Microeconomics - - General - - - General
- D83 - Microeconomics - - Information, Knowledge, and Uncertainty - - - Search, Learning, and Information
This paper has been announced in the following NEP Reports:
- NEP-ALL-2002-04-03 (All new papers)
- NEP-CMP-2002-04-03 (Computational Economics)
- NEP-MIC-2002-04-03 (Microeconomics)
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.:
- Stahl, Dale II & Wilson, Paul W., 1994. "Experimental evidence on players' models of other players," Journal of Economic Behavior & Organization, Elsevier, vol. 25(3), pages 309-327, December.
- Stahl Dale O. & Wilson Paul W., 1995.
"On Players' Models of Other Players: Theory and Experimental Evidence,"
Games and Economic Behavior,
Elsevier, vol. 10(1), pages 218-254, July.
- Dale O. Stahl & Paul W. Wilson, 2010. "On Players' Models of Other Players: Theory and Experimental Evidence," Levine's Working Paper Archive 542, David K. Levine.
- Miguel Costa-Gomes & Vincent P. Crawford & Bruno Broseta, .
"Cognition and Behavior in Normal-Form Games:An Experimental Study,"
00/45, Department of Economics, University of York.
- Costa-Gomes, Miguel & Crawford, Vincent P & Broseta, Bruno, 2001. "Cognition and Behavior in Normal-Form Games: An Experimental Study," Econometrica, Econometric Society, vol. 69(5), pages 1193-1235, September.
- Broseta, Bruno & Costa-Gomes, Miguel & Crawford, Vincent P., 2000. "Cognition and Behavior in Normal-Form Games: An Experimental Study," University of California at San Diego, Economics Working Paper Series qt0fp8278k, Department of Economics, UC San Diego.
- Costa-Gomes, Miguel & Crawford, Vincent P. & Broseta, Bruno, 1998. "Cognition and Behavior in Normal-Form Games: An Experimental Study," University of California at San Diego, Economics Working Paper Series qt1vn4h7x5, Department of Economics, UC San Diego.
- Gilboa, Itzhak, 1988. "The complexity of computing best-response automata in repeated games," Journal of Economic Theory, Elsevier, vol. 45(2), pages 342-352, August.
- Ben-porath, Elchanan, 1990. "The complexity of computing a best response automaton in repeated games with mixed strategies," Games and Economic Behavior, Elsevier, vol. 2(1), pages 1-12, March.
- Fabrizio Germano, 2007. "Stochastic Evolution of Rules for Playing Finite Normal Form Games," Theory and Decision, Springer, vol. 62(4), pages 311-333, May.
- Spiliopoulos, Leonidas, 2009. "Neural networks as a learning paradigm for general normal form games," MPRA Paper 16765, University Library of Munich, Germany.
- Leonidas Spiliopoulos, 2005. "Can the human mind learn to backward induce? A neural network answer," Game Theory and Information 0505008, EconWPA.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Howard Cobb).
If references are entirely missing, you can add them using this form.