Thresholding Bandit with Optimal Aggregate Regret.

Chao Tao Saúl A. Blanco Jian Peng Yuan Zhou

Published in: CoRR (2019)

Keyphrases

regret bounds
worst case
multi armed bandit
dynamic programming
bandit problems
lower bound
online learning
optimal solution
closed form
asymptotically optimal
minimax regret
image processing
edge detection
binary classification
upper confidence bound