Near-optimal Per-Action Regret Bounds for Sleeping Bandits

arXiv:2403.01315v1 Announce Type: new
Abstract: We derive near-optimal per-action regret bounds for sleeping bandits, in which both the sets of available arms and their losses in every round are chosen by an adversary. In a setting with $K$ total arms and at most $A$ available arms in each round over $T$ rounds, the best known upper bound is $O(K\sqrt{TA\ln{K}})$, obtained indirectly via minimizing internal sleeping regrets. Compared to the minimax $\Omega(\sqrt{TA})$ lower bound, this upper bound contains an extra multiplicative …

abstract arxiv cs.lg every losses near per stat.ml total type