Rotting Infinitely Many-armed Bandits beyond the Worst-case Rotting: An Adaptive Approach

arXiv:2404.14202v1 Announce Type: new
Abstract: In this study, we consider the infinitely many armed bandit problems in rotting environments, where the mean reward of an arm may decrease with each pull, while otherwise, it remains unchanged. We explore two scenarios capturing problem-dependent characteristics regarding the decay of rewards: one in which the cumulative amount of rotting is bounded by $V_T$, referred to as the slow-rotting scenario, and the other in which the number of rotting instances is bounded by $S_T$, …

abstract arm arxiv beyond case cs.lg environments explore mean stat.ml study type