Multi-armed Bandit, Dynamic Environments and Meta-Bandits

Cédric Hartland 1, 2 Sylvain Gelly 1, 2 Nicolas Baskiotis 1, 2 Olivier Teytaud 1, 2 Michèle Sebag 1, 2
2 TANC - Algorithmic number theory for cryptology
LIX - Laboratoire d'informatique de l'École polytechnique [Palaiseau], Inria Saclay - Ile de France
Abstract : This paper presents the Adapt-EvE algorithm, extending the UCBT online learning algorithm (Auer et al. 2002) to abruptly changing environments. Adapt-EvE features an adaptive change-point detection test based on Page-Hinkley statistics, and two alternative xtra-exploration procedures respectively based on smooth-restart and Meta-Bandits.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

Cited literature [8 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00113668
Contributor : Cédric Hartland <>
Submitted on : Tuesday, November 14, 2006 - 10:48:45 AM
Last modification on : Monday, December 9, 2019 - 5:24:01 PM
Long-term archiving on: Tuesday, April 6, 2010 - 6:45:15 PM

Identifiers

  • HAL Id : hal-00113668, version 1

Collections

Citation

Cédric Hartland, Sylvain Gelly, Nicolas Baskiotis, Olivier Teytaud, Michèle Sebag. Multi-armed Bandit, Dynamic Environments and Meta-Bandits. 2006. ⟨hal-00113668⟩

Share

Metrics

Record views

1016

Files downloads

1250