IDEAS home Printed from https://ideas.repec.org/p/zur/iewwpx/196.html
   My bibliography  Save this paper

A Learning Theory for the Harsanyi's Doctrine in Repeated Games

Author

Listed:
  • Patrick Leoni

Abstract

This paper investigates simultaneous learning about both nature and others' actions in repeated games, and identifies a set of sufficient conditions assuring that equilibrium actions converge to a Nash equilibrium. Players have each an utility function over infinite histories continuous for the product topology. Nature' drawing after any history can depend on any past actions, or can be independent of them. Provided that 1) every player maximizes her expected payoff against her own beliefs, 2) every player updates her beliefs in a Bayesian manner, 3) prior beliefs about both nature and other players' strategies have a grain of truth, and 4) beliefs about nature are independent of actions chosen during the game, we show that after some finite time the equilibrium outcome of the above game is arbitrarily close to a Nash equilibrium. Those assumptions are shown to be tight.

Suggested Citation

  • Patrick Leoni, "undated". "A Learning Theory for the Harsanyi's Doctrine in Repeated Games," IEW - Working Papers 196, Institute for Empirical Research in Economics - University of Zurich.
    • Handle: RePEc:zur:iewwpx:196
    as

    Download full text from publisher

    File URL: https://www.econ.uzh.ch/apps/workingpapers/wp/iewwp196.pdf
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Jordan, J. S., 1991. "Bayesian learning in normal form games," Games and Economic Behavior, Elsevier, vol. 3(1), pages 60-81, February.
    2. Fudenberg, Drew & Levine, David K, 1993. "Self-Confirming Equilibrium," Econometrica, Econometric Society, vol. 61(3), pages 523-545, May.
    3. Kalai, Ehud & Lehrer, Ehud, 1993. "Rational Learning Leads to Nash Equilibrium," Econometrica, Econometric Society, vol. 61(5), pages 1019-1045, September.
    4. Sandroni, Alvaro, 1998. "Does Rational Learning Lead to Nash Equilibrium in Finitely Repeated Games?," Journal of Economic Theory, Elsevier, vol. 78(1), pages 195-218, January.
    5. John C Harsanyi, 1997. "Games with incomplete information played by "bayesian" players," Levine's Working Paper Archive 1175, David K. Levine.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Bruno S. Frey & Simon Luechinger & Alois Stutzer, 2007. "Calculating Tragedy: Assessing The Costs Of Terrorism," Journal of Economic Surveys, Wiley Blackwell, vol. 21(1), pages 1-24, February.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Mario Gilli, 2002. "Rational Learning in Imperfect Monitoring Games," Working Papers 46, University of Milano-Bicocca, Department of Economics, revised Mar 2002.
    2. Jehiel, Philippe, 1998. "Learning to Play Limited Forecast Equilibria," Games and Economic Behavior, Elsevier, vol. 22(2), pages 274-298, February.
    3. Yoo, Seung Han, 2014. "Learning a population distribution," Journal of Economic Dynamics and Control, Elsevier, vol. 48(C), pages 188-201.
    4. Leoni Patrick L, 2009. "A Constructive Proof that Learning in Repeated Games Leads to Nash Equilibria," The B.E. Journal of Theoretical Economics, De Gruyter, vol. 8(1), pages 1-20, January.
    5. Kalai, Ehud & Lehrer, Ehud, 1995. "Subjective games and equilibria," Games and Economic Behavior, Elsevier, vol. 8(1), pages 123-163.
    6. Matthew O. Jackson & Ehud Kalai, 1997. "False Reputation in a Society of Players," Discussion Papers 1184R, Northwestern University, Center for Mathematical Studies in Economics and Management Science.
    7. Roth, Alvin E. & Erev, Ido, 1995. "Learning in extensive-form games: Experimental data and simple dynamic models in the intermediate term," Games and Economic Behavior, Elsevier, vol. 8(1), pages 164-212.
    8. Jackson, Matthew O. & Kalai, Ehud, 1999. "Reputation versus Social Learning," Journal of Economic Theory, Elsevier, vol. 88(1), pages 40-59, September.
    9. Schipper, Burkhard C., 2021. "Discovery and equilibrium in games with unawareness," Journal of Economic Theory, Elsevier, vol. 198(C).
    10. Philippe Aghion & Ernst Fehr & Richard Holden & Tom Wilkening, 2018. "The Role of Bounded Rationality and Imperfect Information in Subgame Perfect Implementation—An Empirical Investigation," Journal of the European Economic Association, European Economic Association, vol. 16(1), pages 232-274.
    11. Alessandro Lizzeri & Marciano Siniscalchi, 2008. "Parental Guidance and Supervised Learning," The Quarterly Journal of Economics, Oxford University Press, vol. 123(3), pages 1161-1195.
    12. Dekel, Eddie & Fudenberg, Drew & Levine, David K., 2004. "Learning to play Bayesian games," Games and Economic Behavior, Elsevier, vol. 46(2), pages 282-303, February.
    13. Kalai, Ehud & Lehrer, Ehud & Smorodinsky, Rann, 1999. "Calibrated Forecasting and Merging," Games and Economic Behavior, Elsevier, vol. 29(1-2), pages 151-169, October.
    14. Koray, Semih & Saglam, Ismail, 2005. "Learning in Bayesian Regulation," MPRA Paper 1899, University Library of Munich, Germany.
    15. Fudenberg, Drew & Levine, David K., 2009. "Self-confirming equilibrium and the Lucas critique," Journal of Economic Theory, Elsevier, vol. 144(6), pages 2354-2371, November.
    16. repec:ebl:ecbull:v:3:y:2007:i:12:p:1-10 is not listed on IDEAS
    17. Macault, Emilien & Scarsini, Marco & Tomala, Tristan, 2022. "Social learning in nonatomic routing games," Games and Economic Behavior, Elsevier, vol. 132(C), pages 221-233.
    18. Eduardo Zambrano, 1999. "Formal Models Of Authority," Rationality and Society, , vol. 11(2), pages 115-138, May.
    19. Manxi Wu & Saurabh Amin & Asuman Ozdaglar, 2021. "Multi-agent Bayesian Learning with Best Response Dynamics: Convergence and Stability," Papers 2109.00719, arXiv.org.
    20. Sobel, Joel, 2000. "Economists' Models of Learning," Journal of Economic Theory, Elsevier, vol. 94(2), pages 241-261, October.
    21. Drew Fudenberg & David K Levine, 2005. "Learning and Belief Based Trading," Levine's Working Paper Archive 618897000000000975, David K. Levine.

    More about this item

    Keywords

    Repeated Games; Continuous Payo�; Bayesian Learning; Harsanyi's Doctrine;
    All these keywords.

    JEL classification:

    • C72 - Mathematical and Quantitative Methods - - Game Theory and Bargaining Theory - - - Noncooperative 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:zur:iewwpx:196. See general information about how to correct material in RePEc.

    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 bibliographic 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.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Severin Oswald (email available below). General contact details of provider: .

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

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.