Exploration via linearly perturbed loss minimisation

arXiv:2311.07565v2 Announce Type: replace
Abstract: We introduce exploration via linear loss perturbations (EVILL), a randomised exploration method for structured stochastic bandit problems that works by solving for the minimiser of a linearly perturbed regularised negative log-likelihood function. We show that, for the case of generalised linear bandits, EVILL reduces to perturbed history exploration (PHE), a method where exploration is done by training on randomly perturbed rewards. In doing so, we provide a simple and clean explanation of when and why …

abstract arxiv case cs.lg exploration function history likelihood linear loss negative show stat.ml stochastic type via