Browsing by Keywords "Bounded regret"
Now showing items 1-2 of 2
-
Combinatorial multi-armed bandit problem with probabilistically triggered arms: a case with bounded regret
(IEEE, 2017-11)In this paper, we study the combinatorial multi-armed bandit problem (CMAB) with probabilistically triggered arms (PTAs). Under the assumption that the arm triggering probabilities (ATPs) are positive for all arms, we prove ... -
Global bandits
(Institute of Electrical and Electronics Engineers, 2018)Multiarmed bandits (MABs) model sequential decision-making problems, in which a learner sequentially chooses arms with unknown reward distributions in order to maximize its cumulative reward. Most of the prior works on MAB ...