Cong Ma, Banghua Zhu, Jiantao Jiao, Martin J. Wainwright. Minimax Off-Policy Evaluation for Multi-Armed Bandits. IEEE Transactions on Information Theory, 68(8):5314-5339, 2022. [doi]
@article{MaZJW22, title = {Minimax Off-Policy Evaluation for Multi-Armed Bandits}, author = {Cong Ma and Banghua Zhu and Jiantao Jiao and Martin J. Wainwright}, year = {2022}, doi = {10.1109/TIT.2022.3162335}, url = {https://doi.org/10.1109/TIT.2022.3162335}, researchr = {https://researchr.org/publication/MaZJW22}, cites = {0}, citedby = {0}, journal = {IEEE Transactions on Information Theory}, volume = {68}, number = {8}, pages = {5314-5339}, }