Learning the Pareto Front Using Bootstrapped Observation Samples

arXiv:2306.00096v2 Announce Type: replace-cross
Abstract: We consider Pareto front identification (PFI) for linear bandits (PFILin), i.e., the goal is to identify a set of arms with undominated mean reward vectors when the mean reward vector is a linear function of the context. PFILin includes the best arm identification problem and multi-objective active learning as special cases. The sample complexity of our proposed algorithm is optimal up to a logarithmic factor. In addition, the regret incurred by our algorithm during the …

abstract arm arxiv context cs.lg front function identification identify linear mean multi-objective observation pareto pfi replace samples set stat.ml type vector vectors