@article{batchreinforcementlearningwitha,
  title = {Batch Reinforcement Learning with a Nonparametric Off-Policy Policy Gradient},
  author = {Samuele Tosatto and João Carvalho and Jan Peters},
  year = {2020},
  eprint = {2010.14771},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2010.14771v3},
}