2011 | OriginalPaper | Buchkapitel
Deviations of Stochastic Bandit Regret
verfasst von : Antoine Salomon, Jean-Yves Audibert
Erschienen in: Algorithmic Learning Theory
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
This paper studies the deviations of the regret in a stochastic multi-armed bandit problem. When the total number of plays
n
is known beforehand by the agent, Audibert et al. (2009) exhibit a policy such that with probability at least 1-1/
n
, the regret of the policy is of order log
n
. They have also shown that such a property is not shared by the popular
ucb1
policy of Auer et al. (2002). This work first answers an open question: it extends this negative result to any anytime policy. The second contribution of this paper is to design anytime robust policies for specific multi-armed bandit problems in which some restrictions are put on the set of possible distributions of the different arms.