SPEED: Experimental Design for Policy Evaluation in Linear Heteroscedastic Bandits

arXiv:2301.12357v3 Announce Type: replace-cross
Abstract: In this paper, we study the problem of optimal data collection for policy evaluation in linear bandits. In policy evaluation, we are given a target policy and asked to estimate the expected reward it will obtain when executed in a multi-armed bandit environment. Our work is the first work that focuses on such optimal data collection strategy for policy evaluation involving heteroscedastic reward noise in the linear bandit setting. We first formulate an optimal design …

abstract arxiv collection cs.lg data data collection design environment evaluation experimental linear paper policy speed stat.ml study type will work