A Unified View of Large-scale Zero-sum Equilibrium Computation
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.
- Publication:
-
arXiv e-prints
- Pub Date:
- November 2014
- DOI:
- 10.48550/arXiv.1411.5007
- arXiv:
- arXiv:1411.5007
- Bibcode:
- 2014arXiv1411.5007W
- Keywords:
-
- Computer Science - Artificial Intelligence;
- Computer Science - Computer Science and Game Theory
- E-Print:
- AAAI Workshop on Computer Poker and Imperfect Information