Efficient learning by implicit exploration in bandit problems with side observations.

Tomás Kocák Gergely Neu Michal Valko Rémi Munos

Published in: NIPS (2014)

Keyphrases

efficient learning
bandit problems
exploration exploitation
multi armed bandits
decision problems
active learning
learning algorithm
membership queries
pattern languages
multi armed bandit problems
relational databases
data mining
np hard
object oriented