Survival Multiarmed Bandits with Bootstrapping Methods
This addresses the dual goal of maximizing rewards and minimizing ruin risk for agents with budget constraints, representing an incremental advancement in bandit algorithms.
The paper tackled the Survival Multiarmed Bandits problem by developing a framework with a ruin aversion component and a bootstrapping method for action value estimation, achieving superior performance over benchmarks in numerical experiments.
The Multiarmed Bandits (MAB) problem has been extensively studied and has seen many practical applications in a variety of fields. The Survival Multiarmed Bandits (S-MAB) open problem is an extension which constrains an agent to a budget that is directly related to observed rewards. As budget depletion leads to ruin, an agent's objective is to both maximize expected cumulative rewards and minimize the probability of ruin. This paper presents a framework that addresses such a dual goal using an objective function balanced by a ruin aversion component. Action values are estimated through a novel approach which consists of bootstrapping samples from previously observed rewards. In numerical experiments, the policies we present outperform benchmarks from the literature.