Risk-Aversion in Multi-armed Bandits

Amir Sani 1 Alessandro Lazaric 1 Rémi Munos 1
1 SEQUEL - Sequential Learning
LIFL - Laboratoire d'Informatique Fondamentale de Lille, Inria Lille - Nord Europe, LAGIS - Laboratoire d'Automatique, Génie Informatique et Signal
Abstract : Stochastic multi--armed bandits solve the Exploration--Exploitation dilemma and ultimately maximize the expected reward. Nonetheless, in many practical problems, maximizing the expected reward is not the most desirable objective. In this paper, we introduce a novel setting based on the principle of risk--aversion where the objective is to compete against the arm with the best risk--return trade--off. This setting proves to be intrinsically more difficult than the standard multi-arm bandit setting due in part to an exploration risk which introduces a regret associated to the variability of an algorithm. Using variance as a measure of risk, we introduce two new algorithms, investigate their theoretical guarantees, and report preliminary empirical results.
Type de document :
[Research Report] 2012
Liste complète des métadonnées

Contributeur : Alessandro Lazaric <>
Soumis le : mercredi 9 janvier 2013 - 19:01:48
Dernière modification le : jeudi 11 janvier 2018 - 06:22:13
Document(s) archivé(s) le : vendredi 31 mars 2017 - 15:52:58


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-00750298, version 1
  • ARXIV : 1301.1936



Amir Sani, Alessandro Lazaric, Rémi Munos. Risk-Aversion in Multi-armed Bandits. [Research Report] 2012. 〈hal-00750298〉



Consultations de la notice


Téléchargements de fichiers