Generic Exploration and K-armed Voting Bandits.

Tanguy Urvoy Fabrice Clérot Raphaël Féraud Sami Naamane

Published in: ICML (2) (2013)

Keyphrases

stochastic systems
domain specific
voting method
generic model
real time
databases
application specific
voting schemes
neural network
decision making
knowledge base
reinforcement learning
special case
exploration strategy