Login / Signup
Upper-Confidence-Bound Algorithms for Active Learning in Multi-Armed Bandits.
Alexandra Carpentier
Alessandro Lazaric
Mohammad Ghavamzadeh
Rémi Munos
Peter Auer
András Antos
Published in:
CoRR (2015)
Keyphrases
</>
active learning
upper confidence bound
multi armed bandits
contextual bandit
worst case
bandit problems
computational complexity
machine learning
social media