January
2015
A Unified View of Large-scale Zero-sum Equilibrium Computation
Authors:
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.
copied = false, 2000);
">
@workshop{Waugh-2015-17186,
author = {Kevin Waugh And J. Andrew (Drew) Bagnell},
title = {A Unified View of Large-scale Zero-sum Equilibrium Computation},
booktitle = {Proceedings of AAAI '15 Workshop on Computer Poker and Imperfect Information},
year = {2015},
month = {January},
}
author = {Kevin Waugh And J. Andrew (Drew) Bagnell},
title = {A Unified View of Large-scale Zero-sum Equilibrium Computation},
booktitle = {Proceedings of AAAI '15 Workshop on Computer Poker and Imperfect Information},
year = {2015},
month = {January},
}