Anytime many-armed bandits - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2007

Anytime many-armed bandits


This paper introduces the many-armed bandit problem (ManAB), where the number of arms is large comparatively to the relevant number of time steps. While the ManAB framework is relevant to many real-world applications, the state of the art does not offer anytime algorithms handling ManAB problems. Both theory and practice suggest that two problem categories must be distinguished; the easy category includes those problems where good arms have reward probability close to 1; the difficult category includes other problems. Two algorithms termed FAILURE and MUCBT are proposed for the ManAB framework. FAILURE and its variants extend the non-anytime approach proposed for the denumerable-armed bandit and non-asymptotic bounds are shown; it works very efficiently for easy ManAB problems. Meanwhile, MUCBT efficiently deals with difficult ManAB problems.
Fichier principal
Vignette du fichier
mabcap2.pdf (972.9 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

inria-00173263 , version 1 (19-09-2007)


  • HAL Id : inria-00173263 , version 1


Olivier Teytaud, Sylvain Gelly, Michèle Sebag. Anytime many-armed bandits. CAP07, 2007, Grenoble, France. ⟨inria-00173263⟩
300 View
356 Download


Gmail Facebook Twitter LinkedIn More