Dynamic Games and Applications

, Volume 2, Issue 1, pp 160–175 | Cite as

Regret Matching with Finite Memory

Open Access


We consider the regret matching process with finite memory. For general games in normal form, it is shown that any recurrent class of the dynamics must be such that the action profiles that appear in it constitute a closed set under the “same or better reply” correspondence (CUSOBR set) that does not contain a smaller product set that is closed under “same or better replies,” i.e., a smaller PCUSOBR set. Two characterizations of the recurrent classes are offered. First, for the class of weakly acyclic games under better replies, each recurrent class is monomorphic and corresponds to each pure Nash equilibrium. Second, for a modified process with random sampling, if the sample size is sufficiently small with respect to the memory bound, the recurrent classes consist of action profiles that are minimal PCUSOBR sets. Our results are used in a robust example that shows that the limiting empirical distribution of play can be arbitrarily far from correlated equilibria for any large but finite choice of the memory bound.


Regret matching Nash equilibria Closed sets under same or better replies Correlated equilibria 


  1. 1.
    Basu K, Weibull JW (1991) Strategy subsets closed under rational behavior. Econ Lett 36:141–146 MathSciNetMATHCrossRefGoogle Scholar
  2. 2.
    Bernheim BD (1984) Rationalizable strategic behavior. Econometrica 52:1007–1028 MathSciNetMATHCrossRefGoogle Scholar
  3. 3.
    Foster DP, Vohra RV (1997) Calibrated learning and correlated equilibrium. Games Econ Behav 21:40–55 MathSciNetMATHCrossRefGoogle Scholar
  4. 4.
    Foster DP, Vohra RV (1998) Asymptotic calibration. Biometrika 85:379–390 MathSciNetMATHCrossRefGoogle Scholar
  5. 5.
    Friedman JW, Mezzetti C (2001) Learning in games by random sampling. J Econ Theory 98:55–84 MathSciNetMATHCrossRefGoogle Scholar
  6. 6.
    Fudenberg D, Levine DK (1995) Universal consistency and cautious fictitious play. J Econ Dyn Control 19:1065–1089 MathSciNetMATHCrossRefGoogle Scholar
  7. 7.
    Fudenberg D, Levine DK (1998) The theory of learning in games. MIT Press, Cambridge MATHGoogle Scholar
  8. 8.
    Fudenberg D, Levine DK (1999) Conditional universal consistency. Games Econ Behav 29:104–130 MathSciNetMATHCrossRefGoogle Scholar
  9. 9.
    Hannan J (1957) Approximation to Bayes risk in repeated play. In: Dresher M et al. (eds) Contributions to the theory of games III. Princeton University Press, Princeton, pp 97–139 Google Scholar
  10. 10.
    Hart S (2005) Adaptive heuristics. Econometrica 73:1401–1430 MathSciNetMATHCrossRefGoogle Scholar
  11. 11.
    Hart S, Mas-Colell A (2000) A simple adaptive procedure leading to correlated equilibrium. Econometrica 68:1127–1150 MathSciNetMATHCrossRefGoogle Scholar
  12. 12.
    Hurkens S (1995) Learning by forgetful players. Games Econ Behav 11:304–329 MathSciNetMATHCrossRefGoogle Scholar
  13. 13.
    Josephson J, Matros A (2004) Stochastic imitation in finite games. Games Econ Behav 49:244–259 MathSciNetMATHCrossRefGoogle Scholar
  14. 14.
    Lehrer E, Solan E (2009) Approachability with bounded memory. Games Econ Behav 66:995–1004 MathSciNetMATHCrossRefGoogle Scholar
  15. 15.
    Marden JR, Arslan G, Shamma JS (2007) Regret based dynamics: convergence in weakly acyclic games. In: AAMAS ’07: proceedings of the 6th international joint conference on autonomous agents and multiagent systems. ACM, New York, pp 194–201 Google Scholar
  16. 16.
    Monderer D, Shapley LS (1996) Potential games. Games Econ Behav 14:124–143 MathSciNetMATHCrossRefGoogle Scholar
  17. 17.
    Pearce DG (1984) Rationalizable strategic behavior and the problem of perfection. Econometrica 52:1029–1050 MathSciNetMATHCrossRefGoogle Scholar
  18. 18.
    Ritzberger K, Weibull JW (1995) Evolutionary selection in normal-form games. Econometrica 63:1371–1399 MathSciNetMATHCrossRefGoogle Scholar
  19. 19.
    Sandholm WH (2009) Evolutionary game theory. In: Meyers R (ed) Encyclopedia of complexity and systems science. Springer, New York, pp 3176–3205 Google Scholar
  20. 20.
    Saran R, Serrano R (2010) Ex-post regret learning in games with fixed and random matching: the case of private values. Working Paper, Brown University. URL: http://www.econ.brown.edu/faculty/serrano/pdfs/wp2010-11.pdf
  21. 21.
    Shapley LS (1964) Some topics in two-person games. In: Dresher M et al. (eds) Advances in game theory. Annals of mathematical studies, vol 52. Princeton University Press, Princeton, pp 1–28 Google Scholar
  22. 22.
    Viossat Y (2007) The replicator dynamics does not lead to correlated equilibria. Games Econ Behav 59:397–407 MathSciNetMATHCrossRefGoogle Scholar
  23. 23.
    Viossat Y (2008) Evolutionary dynamics may eliminate all strategies used in correlated equilibrium. Math Soc Sci 56:27–43 MathSciNetMATHCrossRefGoogle Scholar
  24. 24.
    Young HP (1993) The evolution of conventions. Econometrica 61:57–84 MathSciNetMATHCrossRefGoogle Scholar
  25. 25.
    Young HP (1998) Individual strategy and social structure. Princeton University Press, Princeton Google Scholar
  26. 26.
    Young HP (2004) Strategic learning and its limits. Oxford University Press, Oxford CrossRefGoogle Scholar
  27. 27.
    Zapechelnyuk A (2008) Better-reply dynamics with bounded recall. Math Oper Res 33:869–879 MathSciNetMATHCrossRefGoogle Scholar

Copyright information

© The Author(s) 2011

Authors and Affiliations

  1. 1.Maastricht UniversityMaastrichtThe Netherlands
  2. 2.Brown UniversityProvidenceUSA
  3. 3.IMDEA Social Sciences InstituteMadridSpain

Personalised recommendations