Efficient Nash Computation in Large Population Games with Bounded Influence
Computer Science and Game Theory
2013-01-07 v1 Artificial Intelligence
Abstract
We introduce a general representation of large-population games in which each player s influence ON the others IS centralized AND limited, but may otherwise be arbitrary.This representation significantly generalizes the class known AS congestion games IN a natural way.Our main results are provably correct AND efficient algorithms FOR computing AND learning approximate Nash equilibria IN this general framework.
Keywords
Cite
@article{arxiv.1301.0577,
title = {Efficient Nash Computation in Large Population Games with Bounded Influence},
author = {Michael Kearns and Yishay Mansour},
journal= {arXiv preprint arXiv:1301.0577},
year = {2013}
}
Comments
Appears in Proceedings of the Eighteenth Conference on Uncertainty in Artificial Intelligence (UAI2002)