Sparse Binary Zero-Sum Games - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2014

Sparse Binary Zero-Sum Games


Solving zero-sum matrix games is polynomial, because it boils down to linear programming. The approximate solving is sublinear by randomized algorithms on machines with random access memory. Algorithms working separately and independently on columns and rows have been proposed, with the same performance; these versions are compliant with matrix games with stochastic reward. (Flory and Teytaud, 2011) has proposed a new version, em-pirically performing better on sparse problems, i.e. cases in which the Nash equilibrium has small support. In this paper, we propose a variant, similar to their work, also dedicated to sparse problems, with provably better bounds than existing methods. We then experiment the method on a card game.
Fichier principal
Vignette du fichier
Auger51.pdf (364.17 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01077627 , version 1 (03-11-2014)


  • HAL Id : hal-01077627 , version 1


David Auger, Jialin Liu, Sylvie Ruette, David L. Saint-Pierre, Olivier Teytaud. Sparse Binary Zero-Sum Games. Asian Conference on Machine Learning, 2014, Ho-Chi-Minh-Ville, Vietnam. pp.16. ⟨hal-01077627⟩
281 View
104 Download


Gmail Facebook Twitter LinkedIn More