Upper Confidence Interval Strategies for Multi-Armed Bandits with Entropy Rewards.

Nir Weinberger Michal Yemini

Published in: ISIT (2022)

Keyphrases

multi armed bandits
bandit problems
reactive planning
mutual information
decision problems
information theoretic
optimal strategy
multi armed bandit
grey relation
object recognition
information theory
computer vision
optimal solution
linear programming