
Efficient learning by implicit exploration in bandit problems with side observations
Author(s) -
Tomáš Kocák,
Gergely Neu,
Michal Valko,
Rémi Munos
Publication year - 2014
Publication title -
hal (le centre pour la communication scientifique directe)
Language(s) - English
Resource type - Conference proceedings
Subject(s) - regret , observability , computer science , action (physics) , online learning , mathematical optimization , artificial intelligence , theoretical computer science , machine learning , mathematics , physics , quantum mechanics , world wide web