Kakade, Sham MFoster, Dean P2023-05-232023-05-232008-02-012016-06-30https://repository.upenn.edu/handle/20.500.14332/47989We 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 play are frequently close to some Nash equilibrium of the game.© 2008. This manuscript version is made available under the CC-BY-NC-ND 4.0 license.Nash equilibriacalibrationcorrelated equilibriagame theorylearningApplied StatisticsBehavioral EconomicsStatistics and ProbabilityTheory and AlgorithmsArticle