Adaptive Estimator Selection for Off-Policy Evaluation
From MaRDI portal
Publication:6335077
arXiv2002.07729MaRDI QIDQ6335077
Author name not available (Why is that?)
Publication date: 18 February 2020
Abstract: We develop a generic data-driven method for estimator selection in off-policy policy evaluation settings. We establish a strong performance guarantee for the method, showing that it is competitive with the oracle estimator, up to a constant factor. Via in-depth case studies in contextual bandits and reinforcement learning, we demonstrate the generality and applicability of the method. We also perform comprehensive experiments, demonstrating the empirical efficacy of our approach and comparing with related approaches. In both case studies, our method compares favorably with existing methods.
Has companion code repository: https://github.com/VowpalWabbit/slope-experiments
This page was built for publication: Adaptive Estimator Selection for Off-Policy Evaluation
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6335077)