Bandits on graphs and structures

Michal Valko 1
1 SEQUEL - Sequential Learning
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Abstract : We investigate the structural properties of certain sequential decision-making problems with limited feedback (bandits) in order to bring the known algorithmic solutions closer to a practical use. In the first part, we put a special emphasis on structures that can be represented as graphs on actions, in the second part we study the large action spaces that can be of exponential size in the number of base actions or even infinite. We show how to take advantage of structures over the actions and (provably) learn faster.
Document type :
Habilitation à diriger des recherches
Complete list of metadatas

Cited literature [128 references]  Display  Hide  Download

https://hal.inria.fr/tel-01359757
Contributor : Michal Valko <>
Submitted on : Sunday, September 4, 2016 - 1:05:04 AM
Last modification on : Friday, March 22, 2019 - 1:33:55 AM
Long-term archiving on : Monday, December 5, 2016 - 12:12:32 PM

Identifiers

  • HAL Id : tel-01359757, version 1

Citation

Michal Valko. Bandits on graphs and structures. Machine Learning [stat.ML]. École normale supérieure de Cachan - ENS Cachan, 2016. ⟨tel-01359757⟩

Share

Metrics

Record views

934

Files downloads

2121