2000 character limit reached
A comparative study of counterfactual estimators (1704.00773v3)
Published 3 Apr 2017 in stat.ML and cs.LG
Abstract: We provide a comparative study of several widely used off-policy estimators (Empirical Average, Basic Importance Sampling and Normalized Importance Sampling), detailing the different regimes where they are individually suboptimal. We then exhibit properties optimal estimators should possess. In the case where examples have been gathered using multiple policies, we show that fused estimators dominate basic ones but can still be improved.