En poursuivant votre navigation sur ce site, vous acceptez l'utilisation d'un simple cookie d'identification. Aucune autre exploitation n'est faite de ce cookie. OK
1

Multi-armed bandits and beyond

Bookmarks Report an error
Multi angle
Authors : Agrawal, Shipra (Author of the conference)
CIRM (Publisher )

Loading the player...

Abstract : In this tutorial I will discuss recent advances in theory of multi-armed bandits and reinforcement learning, in particular the upper confidence bound (UCB) and Thompson Sampling (TS) techniques for algorithm design and analysis.

Keywords : multi-armed bandits; online decision making; learning

MSC Codes :
60J20 - Applications of Markov chains and discrete-time Markov processes on general state spaces
68Q32 - Computational learning theory
68T05 - Learning and adaptive systems

    Information on the Video

    Film maker : Petit, Jean
    Language : English
    Available date : 21/06/2022
    Conference Date : 23/05/2022
    Subseries : Research School
    arXiv category : Machine Learning ; Artificial Intelligence
    Mathematical Area(s) : Computer Science ; Probability & Statistics
    Format : MP4 (.mp4) - HD
    Video Time : 00:53:59
    Targeted Audience : Researchers ; Graduate Students ; Doctoral Students, Post-Doctoral Students
    Download : https://videos.cirm-math.fr/2022-05-23_Agrawal.mp4

Information on the Event

Event Title : Theoretical Computer Science Spring School: Machine Learning / Ecole de Printemps d'Informatique Théorique : Apprentissage Automatique
Event Organizers : Cappé, Olivier ; Garivier, Aurélien ; Gribonval, Rémi ; Kaufmann, Emilie ; Vernade, Claire
Dates : 23/05/2022 - 27/05/2022
Event Year : 2022
Event URL : https://conferences.cirm-math.fr/2542.html

Citation Data

DOI : 10.24350/CIRM.V.19921203
Cite this video as: Agrawal, Shipra (2022). Multi-armed bandits and beyond. CIRM. Audiovisual resource. doi:10.24350/CIRM.V.19921203
URI : http://dx.doi.org/10.24350/CIRM.V.19921203

See Also

Bibliography



Imagette Video

Bookmarks Report an error