A Unified View of Large-scale Zero-sum Equilibrium Computation
Artificial Intelligence
2014-11-19 v1 Computer Science and Game Theory
Abstract
The task of computing approximate Nash equilibria in large zero-sum extensive-form games has received a tremendous amount of attention due mainly to the Annual Computer Poker Competition. Immediately after its inception, two competing and seemingly different approaches emerged---one an application of no-regret online learning, the other a sophisticated gradient method applied to a convex-concave saddle-point formulation. Since then, both approaches have grown in relative isolation with advancements on one side not effecting the other. In this paper, we rectify this by dissecting and, in a sense, unify the two views.
Keywords
Cite
@article{arxiv.1411.5007,
title = {A Unified View of Large-scale Zero-sum Equilibrium Computation},
author = {Kevin Waugh and J. Andrew Bagnell},
journal= {arXiv preprint arXiv:1411.5007},
year = {2014}
}
Comments
AAAI Workshop on Computer Poker and Imperfect Information