[1]
Chandak, Y., Shankar, S. and Thomas, P.S. 2021. High-Confidence Off-Policy (or Counterfactual) Variance Estimation. Proceedings of the AAAI Conference on Artificial Intelligence. 35, 8 (May 2021), 6939-6947. DOI:https://doi.org/10.1609/aaai.v35i8.16855.