@inproceedings{NEURIPS2021_2a800952, author = {Tang, Yunhao and Kozuno, Tadashi and Rowland, Mark and Munos, Remi and Valko, Michal}, booktitle = {Advances in Neural Information Processing Systems}, editor = {M. Ranzato and A. Beygelzimer and Y. Dauphin and P.S. Liang and J. Wortman Vaughan}, pages = {5303--5315}, publisher = {Curran Associates, Inc.}, title = {Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy Evaluation}, url = {https://proceedings.neurips.cc/paper_files/paper/2021/file/2a8009525763356ad5e3bb48b7475b4d-Paper.pdf}, volume = {34}, year = {2021} }