@inproceedings{variationalpolicygradientmethodfor,
  title = {Variational Policy Gradient Method for Reinforcement Learning with General Utilities},
  author = {Junyu Zhang and Alec Koppel and Amrit Singh Bedi and Csaba Szepesvari and Mengdi Wang},
  year = {2020},
  booktitle = {NeurIPS 2020 12},
  eprint = {2007.02151},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2007.02151v1},
}