Yu-Xiang Wang, Alekh Agarwal, Miroslav Dudík
Optimal and Adaptive Off-policy Evaluation in Contextual Bandits
ICML, 2017.
@inproceedings{ICML-2017-WangAD, author = "Yu-Xiang Wang and Alekh Agarwal and Miroslav Dudík", booktitle = "{Proceedings of the 34th International Conference on Machine Learning}", ee = "http://proceedings.mlr.press/v70/wang17a.html", pages = "3589--3597", publisher = "{PMLR}", title = "{Optimal and Adaptive Off-policy Evaluation in Contextual Bandits}", year = 2017, }