One Arrow, Two Kills: An Unified Framework for Achieving Optimal Regret Guarantees in Sleeping Bandits. (arXiv:2210.14998v1 [cs.LG])

We address the problem of \emph{`Internal Regret'} in \emph{Sleeping Bandits}
in the fully adversarial setup, as well as draw connections between different
existing notions of sleeping regrets in the multiarmed bandits (MAB) literature
and consequently analyze the implications: Our first contribution is to propose
the new notion of \emph{Internal Regret} for sleeping MAB. We then proposed an
algorithm that yields sublinear regret in that measure, even for a completely
adversarial sequence of losses and availabilities. We further show that a …

arrow arxiv framework