PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Robust approachability and regret minimization in games with partial monitoring
Vianney Perchet, Shie Mannor and Gilles Stoltz
Submitted article 2011.

Abstract

Approachability has become a standard tool in analyzing learning algorithms in the adversarial online learning setup. We develop a variant of approachability for games where there is ambiguity in the obtained reward that belongs to a set, rather than being a single vector. Using this variant we tackle the problem of approachability in games with partial monitoring and develop simple and efficient algorithms for this setup. We finally consider external and internal regret in repeated games with partial monitoring, for which we show efficient regret-minimizing strategies based on approachability theory.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:7307
Deposited By:Gilles Stoltz
Deposited On:17 March 2011