@inproceedings{NEURIPS2020_75df6360, author = {Kallus, Nathan and Uehara, Masatoshi}, booktitle = {Advances in Neural Information Processing Systems}, editor = {H. Larochelle and M. Ranzato and R. Hadsell and M.F. Balcan and H. Lin}, pages = {10420--10430}, publisher = {Curran Associates, Inc.}, title = {Doubly Robust Off-Policy Value and Gradient Estimation for Deterministic Policies}, url = {https://proceedings.neurips.cc/paper_files/paper/2020/file/75df63609809c7a2052fdffe5c00a84e-Paper.pdf}, volume = {33}, year = {2020} }