@inproceedings{unifyinggradientestimatorsformeta,
  title = {Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy Evaluation},
  author = {Yunhao Tang and Tadashi Kozuno and Mark Rowland and Rémi Munos and Michal Valko},
  year = {2021},
  booktitle = {NeurIPS 2021 12},
  eprint = {2106.13125},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2106.13125v2},
}