Abstract
We provide a natural learning process in which the joint frequency of empirical play converges into the set of convex combinations of Nash equilibria. In this process, all players rationally choose their actions using a public prediction made by a deterministic, weakly calibrated algorithm. Furthermore, the public predictions used in any given round of play are frequently close to some Nash equilibrium of the game.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Billingsley, P.: Convergence of Probability Measures. John Wiley and sons, Chichester (1968)
Dawid, A.P.: The well-calibrated bayesian. Journal of the Am. Stat. Assoc. 77 (1982)
Dawid, A.P.: The impossibility of inductive inference. Journal of the Am. Stat. Assoc. 80 (1985)
Foster, D., Vohra, R.: Calibrated learning and correlated equilibrium. Games and Economic Behavior (1997)
Foster, D., Vohra, R.V.: Asymptotic calibration. Biometrika 85 (1998)
Foster, D.P., Young, H.P.: On the impossibility of predicting the behavior of rational agents. Proceedings of the National Academy of Sciences 98 (2001)
Foster, D. P., Young, H. P.: Learning, hypothesis testing, and nash equilibrium (forthcoming)
Freund, Y., Schapire, R.: Adaptive game playing using multiplicative weights. Games and Economic Behavior 29 (1999)
Fudenberg, D., Levine, D.: The Theory of Learning in Games. MIT Press, Cambridge (1998)
Hart, S., Mas-Colell, A.: A simple adaptive procedure leading to corre latedequilibrium. Econometrica 68 (2000)
Hart, S., Mas-Colell, A.: Uncoupled dynamics do not lead to nash equilibrium. American Economic Review 93, 1830–1836 (2003)
Kalai, E., Lehrer, E.: Rational learning leads to nash equilibrium. Econometrica (1993)
Kalai, E., Lehrer, E., Smorodinsky, R.: Calibrated forecasting and merging. Games and Economic Behavior 29 (1999)
Milgrom, P., Roberts, J.: Adaptive and sophisticated learning in normal form games. Games and Economic Behavior 3, 82–100 (1991)
Oakes, D.: Self-calibrating priors do not exist. Journal of the Am. Stat. Assoc. 80 (1985)
Robinson, J.: An iterative method of solving a game. Ann. Math. (1951)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kakade, S.M., Foster, D.P. (2004). Deterministic Calibration and Nash Equilibrium. In: Shawe-Taylor, J., Singer, Y. (eds) Learning Theory. COLT 2004. Lecture Notes in Computer Science(), vol 3120. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-27819-1_3
Download citation
DOI: https://doi.org/10.1007/978-3-540-27819-1_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22282-8
Online ISBN: 978-3-540-27819-1
eBook Packages: Springer Book Archive