Geodesic
Online Learning and Game Theory. A Quick Overview with recent results and applications
Mathieu Faure1 ; Pierre Gaillard2 ; Bruno Gaujal3 ; Vianney Perchet4
1 Aix-Marseille University, CNRS and EHESS, Centre de la vieille Charité, 2 rue de la Charité, 13002 Marseille, France
2 EDF R&D, Clamart, France & GREGHEC (HEC Paris, CNRS), Jouy-en-Josas, France
3 INRIA Grenoble Rhône-Alpes, LIG laboratoire d’Informatique de Grenoble, MESCAL
4 Laboratoire de Probabiliés et Modèles Aléatoires, Université Paris Diderot, Paris, France & Equipe Sierra, INRIA - ENS Paris, Paris, France
ESAIM. Proceedings, Tome 51 (2015), pp. 246-271.

Voir la notice de l'article provenant de la source EDP Sciences

We study one of the main concept of online learning and sequential decision problem known as regret minimization. We investigate three different frameworks, whether data are generated accordingly to some i.i.d. process, or when no assumption whatsoever are made on their generation and, finally, when they are the consequences of some sequential interactions between players. The overall objective is to provide a comprehensive introduction to this domain. In each of these main setups, we define and analyze classical algorithms and we analyze their performances. Finally, we also show that some concepts of equilibria that emerged in game theory are learnable by players using online learning schemes while some other concepts are not learnable.
DOI : 10.1051/proc/201551014

Mathieu Faure 1 ; Pierre Gaillard 2 ; Bruno Gaujal 3 ; Vianney Perchet 4

1 Aix-Marseille University, CNRS and EHESS, Centre de la vieille Charité, 2 rue de la Charité, 13002 Marseille, France
2 EDF R&D, Clamart, France & GREGHEC (HEC Paris, CNRS), Jouy-en-Josas, France
3 INRIA Grenoble Rhône-Alpes, LIG laboratoire d’Informatique de Grenoble, MESCAL
4 Laboratoire de Probabiliés et Modèles Aléatoires, Université Paris Diderot, Paris, France & Equipe Sierra, INRIA - ENS Paris, Paris, France 
@article{EP_2015_51_a14,
     author = {Mathieu Faure and Pierre Gaillard and Bruno Gaujal and Vianney Perchet},
     title = {Online {Learning} and {Game} {Theory.} {A} {Quick} {Overview} with recent results and applications},
     journal = {ESAIM. Proceedings},
     pages = {246--271},
     publisher = {mathdoc},
     volume = {51},
     year = {2015},
     doi = {10.1051/proc/201551014},
     language = {en},
     url = {http://geodesic.mathdoc.fr/articles/10.1051/proc/201551014/}
}
TY  - JOUR
AU  - Mathieu Faure
AU  - Pierre Gaillard
AU  - Bruno Gaujal
AU  - Vianney Perchet
TI  - Online Learning and Game Theory. A Quick Overview with recent results and applications
JO  - ESAIM. Proceedings
PY  - 2015
SP  - 246
EP  - 271
VL  - 51
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/articles/10.1051/proc/201551014/
DO  - 10.1051/proc/201551014
LA  - en
ID  - EP_2015_51_a14
ER  - 
%0 Journal Article
%A Mathieu Faure
%A Pierre Gaillard
%A Bruno Gaujal
%A Vianney Perchet
%T Online Learning and Game Theory. A Quick Overview with recent results and applications
%J ESAIM. Proceedings
%D 2015
%P 246-271
%V 51
%I mathdoc
%U http://geodesic.mathdoc.fr/articles/10.1051/proc/201551014/
%R 10.1051/proc/201551014
%G en
%F EP_2015_51_a14
Mathieu Faure; Pierre Gaillard; Bruno Gaujal; Vianney Perchet. Online Learning and Game Theory. A Quick Overview with recent results and applications. ESAIM. Proceedings, Tome 51 (2015), pp. 246-271. doi : 10.1051/proc/201551014. http://geodesic.mathdoc.fr/articles/10.1051/proc/201551014/

Cité par Sources :