@article{combingpolicyevaluationandpolicy,
  title = {The $f$-Divergence Reinforcement Learning Framework},
  author = {Chen Gong and Qiang He and Yunpeng Bai and Zhou Yang and Xiaoyu Chen and Xinwen Hou and Xianjie Zhang and Yu Liu and Guoliang Fan},
  year = {2021},
  eprint = {2109.11867},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2109.11867v2},
}