The New Palgrave Dictionary of Economics

2018 Edition
| Editors: Macmillan Publishers Ltd

Learning and Evolution in Games: Belief Learning

  • John Nachbar
Reference work entry


In the context of learning in games, belief learning refers to models in which players are engaged in a dynamic game and each player optimizes with respect to a prediction rule that gives a forecast of next-period opponent behaviour as a function of the current history. This article focuses on the most studied class of dynamic games, namely, two-player discounted repeated games with finite stage game action sets and perfect monitoring.


Belief learning Best-response dynamics Convergence Cournot, A. A. Distributional strategies Dynamic games Fictitious play Folk theorem Learnable best-response property Mixed strategy equilibrium Myopia Perfect monitoring Prediction rules Purification Repeated games 

JEL Classifications

This is a preview of subscription content, log in to check access.


  1. Aoyagi, M. 1996. Evolution of beliefs and the Nash equilibrium of normal form games. Journal of Economic Theory 70: 444–469.CrossRefGoogle Scholar
  2. Bernheim, B.D. 1984. Rationalizable strategic behavior. Econometrica 52: 1007–1028.CrossRefGoogle Scholar
  3. Brown, G.W. 1951. Iterative solutions of games by fictitious play. In Activity analysis of production and allocation, ed. T.J. Koopmans. New York: Wiley.Google Scholar
  4. Cournot, A. 1838. Researches into the Mathematical Principles of the Theory of Wealth. Trans. N.T. Bacon, New York: Kelley, 1960.Google Scholar
  5. Dawid, A.P. 1985. The impossibility of inductive inference. Journal of the American Statistical Association 80: 340–341.Google Scholar
  6. Foster, D., and P. Young. 2001. On the impossibility of predicting the behavior of rational agents. Proceedings of the National Academy of Sciences 98: 12848–12853.CrossRefGoogle Scholar
  7. Foster, D., and P. Young. 2003. Learning, hypothesis testing, and Nash equilibrium. Games and Economic Behavior 45: 73–96.CrossRefGoogle Scholar
  8. Fudenberg, D., and D. Kreps. 1993. Learning mixed equilibria. Games and Economic Behavior 5: 320–367.CrossRefGoogle Scholar
  9. Fudenberg, D., and D. Levine. 1993. Steady state learning and Nash equilibrium. Econometrica 61: 547–574.CrossRefGoogle Scholar
  10. Fudenberg, D., and D. Levine. 1995. Universal consistency and cautious fictitious play. Journal of Economic Dynamics and Control 19: 1065–1089.CrossRefGoogle Scholar
  11. Fudenberg, D., and D. Levine. 1998. Theory of learning in games. Cambridge, MA: MIT Press.Google Scholar
  12. Fudenberg, D., and D. Levine. 1999. Conditional universal consistency. Games and Economic Behavior 29: 104–130.CrossRefGoogle Scholar
  13. Harsanyi, J. 1973. Games with randomly disturbed payoffs: A new rationale for mixed-strategy equilibrium points. International Journal of Game Theory 2: 1–23.CrossRefGoogle Scholar
  14. Hart, S., and A. Mas-Colell. 2003. Uncoupled dynamics do not lead to Nash equilibrium. American Economic Review 93: 1830–1836.CrossRefGoogle Scholar
  15. Hart, S., and A. Mas-Colell. 2006. Stochastic uncoupled dynamics and Nash equilibrium. Games and Economic Behavior 57: 286–303.CrossRefGoogle Scholar
  16. Hofbauer, J., and W. Sandholm. 2002. On the global convergence of stochastic fictitious play. Econometrica 70: 2265–2294.CrossRefGoogle Scholar
  17. Jackson, M., and E. Kalai. 1999. False reputation in a society of players. Journal of Economic Theory 88: 40–59.CrossRefGoogle Scholar
  18. Jordan, J.S. 1991. Bayesian learning in normal form games. Games and Economic Behavior 3: 60–81.CrossRefGoogle Scholar
  19. Jordan, J.S. 1993. Three problems in learning mixed-strategy Nash equilibria. Games and Economic Behavior 5: 368–386.CrossRefGoogle Scholar
  20. Jordan, J.S. 1995. Bayesian learning in repeated games. Games and Economic Behavior 9: 8–20.CrossRefGoogle Scholar
  21. Kalai, E., and E. Lehrer. 1993a. Rational learning leads to Nash equilibrium. Econometrica 61: 1019–1045.CrossRefGoogle Scholar
  22. Kalai, E., and E. Lehrer. 1993b. Subjective equilibrium in repeated games. Econometrica 61: 1231–1240.CrossRefGoogle Scholar
  23. Kuhn, H.W. 1964. Extensive games and the problem of information. In Contributions to the theory of games, ed. M. Dresher, L.S. Shapley, and A.W. Tucker, Vol. 2. Princeton: Princeton University Press.Google Scholar
  24. Milgrom, P., and J. Roberts. 1991. Adaptive and sophisticated learning in repeated normal form games. Games and Economic Behavior 3: 82–100.CrossRefGoogle Scholar
  25. Milgrom, P., and R. Weber. 1985. Distributional strategies for games with incomplete information. Mathematics of Operations Research 10: 619–632.CrossRefGoogle Scholar
  26. Nachbar, J.H. 2001. Bayesian learning in repeated games of incomplete information. Social Choice and Welfare 18: 303–326.CrossRefGoogle Scholar
  27. Nachbar, J.H. 2005. Beliefs in repeated games. Econometrica 73: 459–480.CrossRefGoogle Scholar
  28. Noguchi, Y. 2005. Merging with a set of probability measures: A characterization. Working paper, Kanto Gakuin University.Google Scholar
  29. Nyarko, Y. 1998. Bayesian learning and convergence to Nash equilibria without common priors. Economic Theory 11: 643–655.CrossRefGoogle Scholar
  30. Oakes, D. 1985. Self-calibrating priors do not exist. Journal of the American Statistical Association 80: 339–342.CrossRefGoogle Scholar
  31. Sandroni, A. 1998. Necessary and sufficient conditions for convergence to Nash equilibrium: the almost absolute continuity hypothesis. Games and Economic Behavior 22: 121–147.CrossRefGoogle Scholar
  32. Sandroni, A. 2000. Reciprocity and cooperation in repeated coordination games: The principled-player approach. Games and Economic Behavior 32: 157–182.CrossRefGoogle Scholar
  33. Shapley, L. 1962. On the nonconvergence of fictitious play. Discussion Paper RM-3026, RAND.Google Scholar

Copyright information

© Macmillan Publishers Ltd. 2018

Authors and Affiliations

  • John Nachbar
    • 1
  1. 1.