@article{greedificationoperatorsforpolicy,
  title = {Greedification Operators for Policy Optimization: Investigating Forward and Reverse KL Divergences},
  author = {Alan Chan and Hugo Silva and Sungsu Lim and Tadashi Kozuno and A. Rupam Mahmood and Martha White},
  year = {2021},
  eprint = {2107.08285},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2107.08285v2},
}