@article{cautiouspolicyprogrammingexploitingkl,
  title = {Cautious Policy Programming: Exploiting KL Regularization in Monotonic Policy Improvement for Reinforcement Learning},
  author = {Lingwei Zhu and Toshinori Kitamura and Takamitsu Matsubara},
  year = {2021},
  eprint = {2107.05798},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2107.05798v3},
}