Best of both worlds: Stochastic & adversarial ...

Document type :
Communication dans un congrès avec actes
Permalink :
http://hdl.handle.net/20.500.12210/23188
Title :
Best of both worlds: Stochastic & adversarial best-arm identification
Author(s) :
Abbasi-Yadkori, Yasin [Auteur]
Adobe Research
Bartlett, Peter [Auteur]
Lawrence Berkeley National Laboratory [Berkeley] [LBNL]
Gabillon, Victor [Auteur]
Queensland University of Technology [Brisbane] [QUT]
Malek, Alan [Auteur]
Massachusetts Institute of Technology [MIT]
Valko, Michal [Auteur] refId
Sequential Learning [SEQUEL]
Conference title :
Conference on Learning Theory
City :
Stockholm
Country :
Suède
Start date of the conference :
2018
English keyword(s) :
multi-armed bandits
adversarial and stochastic rewards
best-arm identification
HAL domain(s) :
Statistiques [stat]/Machine Learning [stat.ML]
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
ANR Project :
Extraction et transfert de connaissances dans l'apprentissage par renforcement
Bayes on a Budget - big data and expensive models
Collections :
Source :
Harvested from HAL
Submission date :
2020-05-28T11:43:59Z
Files
Thumbnail