Bandits on graphs and structures - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Habilitation À Diriger Des Recherches Year : 2016

Bandits on graphs and structures

Michal Valko

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.
Fichier principal
Vignette du fichier
valko2016bandits.pdf (10.2 Mo) Télécharger le fichier
Loading...

Dates and versions

tel-01359757 , version 1 (04-09-2016)

Identifiers

  • HAL Id : tel-01359757 , version 1

Cite

Michal Valko. Bandits on graphs and structures. Machine Learning [stat.ML]. École normale supérieure de Cachan - ENS Cachan, 2016. ⟨tel-01359757⟩
769 View
2396 Download

Share

Gmail Mastodon Facebook X LinkedIn More