Gap-free Bounds for Stochastic Multi-Armed Bandit - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2008

Gap-free Bounds for Stochastic Multi-Armed Bandit

Résumé

We consider the stochastic multi-armed bandit problem with unknown horizon. We present a randomized decision strategy which is based on updating a probability distribution through a stochastic mirror descent/exponentiated gradient type algorithm. We consider separately two assumptions: nonnegative losses or arbitrary losses with an exponential moment condition. We prove optimal (up to logarithmic factors) gap-free bounds on the excess risk of the average over time of the instantaneous losses induced by the choice of a specific action.
Fichier non déposé

Dates et versions

hal-00317655 , version 1 (03-09-2008)

Identifiants

Citer

Anatoli B. Juditsky, Alexander Nazin, Alexandre Tsybakov, Nicolas Vayatis. Gap-free Bounds for Stochastic Multi-Armed Bandit. 17th World IFAC Congress, Jul 2008, Seoul, South Korea. pp.11560-11563, ⟨10.3182/20080706-5-KR-1001.01959⟩. ⟨hal-00317655⟩
111 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More