Bounded Regret for Finitely Parameterized Multi-Armed Bandits.

Kishan Panaganti Dileep M. Kalathil

Published in: IEEE Control. Syst. Lett. (2021)

Keyphrases

multi armed bandits
bandit problems
multi armed bandit
decision problems
finite number
multi armed bandit problems
learning algorithm
bayesian networks
probability distribution
inductive inference