IDEAS home Printed from https://ideas.repec.org/p/pra/mprapa/16765.html
   My bibliography  Save this paper

Neural networks as a learning paradigm for general normal form games

Author

Listed:
  • Spiliopoulos, Leonidas

Abstract

This paper addresses how neural networks learn to play one-shot normal form games through experience in an environment of randomly generated game payoffs and randomly selected opponents. This agent based computational approach allows the modeling of learning all strategic types of normal form games, irregardless of the number of pure and mixed strategy Nash equilibria that they exhibit. This is a more realistic model of learning than the oft used models in the game theory learning literature which are usually restricted either to repeated games against the same opponent (or games with different payoffs but belonging to the same strategic class). The neural network agents were found to approximate human behavior in experimental one-shot games very well as the Spearman correlation coefficients between their behavior and that of human subjects ranged from 0.49 to 0.8857 across numerous experimental studies. Also, they exhibited the endogenous emergence of heuristics that have been found effective in describing human behavior in one-shot games. The notion of bounded rationality is explored by varying the topologies of the neural networks, which indirectly affects their ability to act as universal approximators of any function. The neural networks' behavior was assessed across various dimensions such as convergence to Nash equilibria, equilibrium selection and adherence to principles of iterated dominance.

Suggested Citation

  • Spiliopoulos, Leonidas, 2009. "Neural networks as a learning paradigm for general normal form games," MPRA Paper 16765, University Library of Munich, Germany.
  • Handle: RePEc:pra:mprapa:16765
    as

    Download full text from publisher

    File URL: https://mpra.ub.uni-muenchen.de/16765/1/MPRA_paper_16765.pdf
    File Function: original version
    Download Restriction: no

    References listed on IDEAS

    as
    1. Ockenfels, Axel & Selten, Reinhard, 2005. "Impulse balance equilibrium and feedback in first price auctions," Games and Economic Behavior, Elsevier, vol. 51(1), pages 155-170, April.
    2. Haruvy, Ernan & Stahl, Dale O., 2004. "Deductive versus inductive equilibrium selection: experimental results," Journal of Economic Behavior & Organization, Elsevier, vol. 53(3), pages 319-331, March.
    3. Yang, Z. R. & Platt, Marjorie B. & Platt, Harlan D., 1999. "Probabilistic Neural Networks in Bankruptcy Prediction," Journal of Business Research, Elsevier, vol. 44(2), pages 67-74, February.
    4. Schotter Andrew & Weigelt Keith & Wilson Charles, 1994. "A Laboratory Investigation of Multiperson Rationality and Presentation Effects," Games and Economic Behavior, Elsevier, vol. 6(3), pages 445-468, May.
    5. Cho, In-Koo & Sargent, Thomas J., 1996. "Neural networks for encoding and adapting in dynamic economies," Handbook of Computational Economics, in: H. M. Amman & D. A. Kendrick & J. Rust (ed.),Handbook of Computational Economics, edition 1, volume 1, chapter 9, pages 441-470, Elsevier.
    6. Fabrizio Germano, 2007. "Stochastic Evolution of Rules for Playing Finite Normal Form Games," Theory and Decision, Springer, vol. 62(4), pages 311-333, May.
    7. Mookherjee, Dilip & Sopher, Barry, 1997. "Learning and Decision Costs in Experimental Constant Sum Games," Games and Economic Behavior, Elsevier, vol. 19(1), pages 97-132, April.
    8. Cabrales, Antonio & Garcia-Fontes, Walter & Motta, Massimo, 2000. "Risk dominance selects the leader: An experimental analysis," International Journal of Industrial Organization, Elsevier, vol. 18(1), pages 137-162, January.
    9. Straub, Paul G., 1995. "Risk dominance and coordination failures in static games," The Quarterly Review of Economics and Finance, Elsevier, vol. 35(4), pages 339-363.
    10. Louviere,Jordan J. & Hensher,David A. & Swait,Joffre D. With contributions by-Name:Adamowicz,Wiktor, 2000. "Stated Choice Methods," Cambridge Books, Cambridge University Press, number 9780521788304, September.
    11. Reinhard Selten & Klaus Abbink & Ricarda Cox, 2005. "Learning Direction Theory and the Winner’s Curse," Experimental Economics, Springer;Economic Science Association, vol. 8(1), pages 5-20, April.
    12. LiCalzi Marco, 1995. "Fictitious Play by Cases," Games and Economic Behavior, Elsevier, vol. 11(1), pages 64-89, October.
    13. Nagel, Rosemarie, 1995. "Unraveling in Guessing Games: An Experimental Study," American Economic Review, American Economic Association, vol. 85(5), pages 1313-1326, December.
    14. Selten, Reinhard, 1998. "Features of experimentally observed bounded rationality," European Economic Review, Elsevier, vol. 42(3-5), pages 413-436, May.
    15. Sgroi, Daniel & Zizzo, Daniel J., 2007. "Neural networks and bounded rationality," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 375(2), pages 717-725.
    16. Pedro Rey Biel, 2005. "Equilibrium PLay and Best Response to (Stated) Beliefs in Constant Sum Games," Experimental 0506003, University Library of Munich, Germany.
    17. Tang, Fang-Fang, 2001. "Anticipatory learning in two-person games: some experimental results," Journal of Economic Behavior & Organization, Elsevier, vol. 44(2), pages 221-232, February.
    18. Tesfatsion, Leigh S., 2002. "Agent-Based Computational Economics: Growing Economies from the Bottom Up," Staff General Research Papers Archive 5075, Iowa State University, Department of Economics.
    19. Kuan, Chung-Ming & Liu, Tung, 1995. "Forecasting Exchange Rates Using Feedforward and Recurrent Neural Networks," Journal of Applied Econometrics, John Wiley & Sons, Ltd., vol. 10(4), pages 347-364, Oct.-Dec..
    20. Reinhard Selten & Klaus Abbink & Ricarda Cox, 2005. "Learning Direction Theory and the Winner’s Curse," Experimental Economics, Springer;Economic Science Association, vol. 8(1), pages 5-20, April.
    21. D. Sgroi & D. J. Zizzo, 2002. "Strategy Learning in 3x3 Games by Neural Networks," Cambridge Working Papers in Economics 0207, Faculty of Economics, University of Cambridge.
    Full references (including those not matched with items on IDEAS)

    More about this item

    Keywords

    Behavioral game theory; Learning; Global games; Neural networks; Agent-based computational economics; Simulations; Complex adaptive systems; Artificial intelligence;

    JEL classification:

    • C45 - Mathematical and Quantitative Methods - - Econometric and Statistical Methods: Special Topics - - - Neural Networks and Related Topics
    • C70 - Mathematical and Quantitative Methods - - Game Theory and Bargaining Theory - - - General
    • C73 - Mathematical and Quantitative Methods - - Game Theory and Bargaining Theory - - - Stochastic and Dynamic Games; Evolutionary Games

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:pra:mprapa:16765. 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: (Joachim Winter). General contact details of provider: http://edirc.repec.org/data/vfmunde.html .

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service hosted by the Research Division of the Federal Reserve Bank of St. Louis . RePEc uses bibliographic data supplied by the respective publishers.