Deterministic calibration and Nash equilibrium

Authors:
Sham M. Kakade;Dean P. Foster
Affiliations:
Toyota Technological Institute, Chicago, IL 60637, USA;University of Pennsylvania, Philadelphia, PA 19104, USA
Venue:
Journal of Computer and System Sciences
Year:
2008

Citing 3
Cited 2

A randomization rule for selecting forecasts

Operations Research
Online calibrated forecasts: Memory efficiency versus universality for learning in games

Machine Learning
Non-asymptotic calibration and resolution

ALT'05 Proceedings of the 16th international conference on Algorithmic Learning Theory

The communication complexity of uncoupled nash equilibrium procedures

Proceedings of the thirty-ninth annual ACM symposium on Theory of computing
A Geometric Proof of Calibration

Mathematics of Operations Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

We provide a natural learning process in which the joint frequency of (time-averaged) empirical play converges into the set of convex combinations of Nash equilibria. Furthermore, the actual distribution of players' actions is close to some (approximate) Nash equilibria on most rounds (on all but a vanishing fraction of the rounds). In this process, all players rationally choose their actions using a public prediction made by a deterministic, weakly calibrated algorithm. For this to be possible, we show that such a deterministic (weakly) calibrated learning algorithm exists.