Residual Bootstrap Exploration for Bandit Algorithms
share
In this paper, we propose a novel perturbation-based exploration method in bandit algorithms with bounded or unbounded rewards, called residual bootstrap exploration (ReBoot). The ReBoot enforces exploration by injecting data-driven randomness through a residual-based perturbation mechanism. This novel mechanism captures the underlying distributional properties of fitting errors, and more importantly boosts exploration to escape from suboptimal solutions (for small sample sizes) by inflating variance level in an unconventional way. In theory, with appropriate variance inflation level, ReBoot provably secures instance-dependent logarithmic regret in Gaussian multi-armed bandits. We evaluate the ReBoot in different synthetic multi-armed bandits problems and observe that the ReBoot performs better for unbounded rewards and more robustly than Giro<cit.> and PHE<cit.>, with comparable computational efficiency to the Thompson sampling method.
READ FULL TEXT