On the Convergence of Fictitious Play

References

• Brown G. W. Some notes on computation of games solutions. (1949) . Report no. P-78, Rand Corporation, Santa Monica, CaliforniaGoogle Scholar
• Brown G. W., Koopmans T. C. Iterative solutions of games by fictitious play. Activity Analysis of Production and Allocation (1951) (Wiley, New York) 374–376Google Scholar
• Crawford V. P. Learning behavior and mixed-strategy Nash equilibria. J. Econom. Behav. Org. (1985) 6:69–78Crossref, Google Scholar
• Foster D., Young H. P.On the nonconvergence of fictitious play in coordination games (1996) . Preprint, Johns Hopkins University, Baltimore, MarylandGoogle Scholar
• Fudenberg D., Kreps D. M. Learning mixed strategy equilibria. Games Econom. Behav. (1993) 5:320–367Crossref, Google Scholar
• Harris C.On the rate of convergence of continuous-time fictitious play (1996) . Preprint, University of Cambridge, CambridgeGoogle Scholar
• Harsanyi J. C. Games with randomly disturbed payoffs. Internat. J. Game Theory (1973a) 2:1–23Crossref, Google Scholar
• Harsanyi J. C. Oddness of the number of equilibrium points: A new proof. Internat. J. Game Theory (1973b) 2:235–250Crossref, Google Scholar
• Hirsch M., Smale S.Differential Equations, Dynamical Systems and Linear Algebra (1974) (Academic Press, New York) Google Scholar
• Hofbauer J.Stability for best response dynamics (1994) (Institut für Mathematik, Universität Wien, Vienna) . PreprintGoogle Scholar
• Hofbauer J., Sigmund K.The Theory of Evolution and Dynamical Systems (1988) (Cambridge University Press, Cambridge) Google Scholar
• Jordan J. S. Three problems in learning mixed strategy equilibria. Games Econom. Behav. (1993) 5:368–386Crossref, Google Scholar
• Metrick A., Polak B. Fictitious play in 2 × 2 games: A geometric proof of convergence. Econom. Theory (1994) 4:923–933Crossref, Google Scholar
• Miyasawa K.On the convergence of the learning process in a 2 × 2 non-zero-sum game (1963) (Princeton). Princeton University Econometric Research Program, Research Memorandum No. 33Google Scholar
• Monderer D., Sela A.Fictitious play and the no-cycling conditions (1993) (The Technion, Haifa) . PreprintGoogle Scholar
• Monderer D., Samet D., Sela A. Belief affirming in learning processes. J. Econom. Theory (1997) 73:438–452Crossref, Google Scholar
• Robinson J. An iterative method of solving a game. Ann. Math. (1951) 54:296–301Crossref, Google Scholar
• Rosenmüller J. Über periodizitätseigenschaften spieltheoretischer Lernprozesse. Z. Wahrscheinlichkeitstheorie Verw. Geb. (1971) 17:259–308Crossref, Google Scholar
• Rubinstein A. Comments on the interpretation of game theory. Econometrica (1991) 59:909–924Crossref, Google Scholar
• Shapley L. S., Dresher M., Shapley L. S., Tucker A. W. Some topics in two-person games. Advances in Game Theory. Ann. of Math. Stud. (1964) 52:1–28Google Scholar
• van Damme E.Stability and Perfection of Nash Equilibria (1991) (Springer-Verlag, Berlin) Crossref, Google Scholar