Statistics Papers

Document Type

Journal Article

Date of this Version

2-2008

Publication Source

Journal of Computer and System Sciences

Volume

74

Issue

1

Start Page

115

Last Page

130

DOI

10.1016/j.jcss.2007.04.017

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 play are frequently close to some Nash equilibrium of the game.

Copyright/Permission Statement

© 2008. This manuscript version is made available under the CC-BY-NC-ND 4.0 license.

Keywords

Nash equilibria, calibration, correlated equilibria, game theory, learning

Share

COinS
 

Date Posted: 27 November 2017

This document has been peer reviewed.