%0 Journal Article %T Online Learning and Game Theory. A quick overview with recent results and applications %+ Groupement de Recherche en Économie Quantitative d'Aix-Marseille (GREQAM) %+ EDF R&D (EDF R&D) %+ Groupement de Recherche et d'Etudes en Gestion (GREGHEC ) %+ Middleware efficiently scalable (MESCAL) %+ Université Grenoble Alpes [2016-2019] (UGA [2016-2019]) %+ Laboratoire de Probabilités et Modèles Aléatoires (LPMA) %A Faure, Mathieu %A Gaillard, Pierre %A Gaujal, Bruno %A Perchet, Vianney %< avec comité de lecture %@ 1270-900X %J ESAIM: Proceedings %I EDP Sciences %V 51 %P 246 - 271 %8 2015-10 %D 2015 %R 10.1051/proc/201551014 %Z Computer Science [cs]/Performance [cs.PF]Journal articles %X 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. %G English %L hal-01237039 %U https://inria.hal.science/hal-01237039 %~ UNIV-PARIS7 %~ UPMC %~ UGA %~ PMA %~ CNRS %~ INRIA %~ UNIV-GRENOBLE1 %~ UNIV-AMU %~ UNIV-PMF_GRENOBLE %~ EHESS %~ INPG %~ INRIA-RHA %~ LIG %~ GREQAM %~ EC-MARSEILLE %~ INSMI %~ INRIA_TEST %~ TESTALAIN1 %~ INRIA2 %~ UPMC_POLE_1 %~ EDF %~ LPSM %~ AMSE %~ INRIA-RENGRE %~ SORBONNE-UNIVERSITE %~ SU-SCIENCES %~ UNIV-PARIS %~ SU-TI %~ LIG_SIDCH %~ ALLIANCE-SU