Rotting Infinitely Many-armed Bandits
Abstract
We consider the infinitely many-armed bandit problem with rotting rewards, where the mean reward of an arm decreases at each pull of the arm according to an arbitrary trend with maximum rotting rate . We show that this learning problem has an worst-case regret lower bound where is the horizon time. We show that a matching upper bound , up to a poly-logarithmic factor, can be achieved by an algorithm that uses a UCB index for each arm and a threshold value to decide whether to continue pulling an arm or remove the arm from further consideration, when the algorithm knows the value of the maximum rotting rate . We also show that an regret upper bound can be achieved by an algorithm that does not know the value of , by using an adaptive UCB index along with an adaptive threshold value.
Keywords
Cite
@article{arxiv.2201.12975,
title = {Rotting Infinitely Many-armed Bandits},
author = {Jung-hun Kim and Milan Vojnovic and Se-Young Yun},
journal= {arXiv preprint arXiv:2201.12975},
year = {2023}
}
Comments
ICML2022