Adaptive Estimator Selection for Off-Policy Evaluation

Understand

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.