@article{ensuringmonotonicpolicyimprovementin,
  title = {Ensuring Monotonic Policy Improvement in Entropy-regularized Value-based Reinforcement Learning},
  author = {Lingwei Zhu and Takamitsu Matsubara},
  year = {2020},
  eprint = {2008.10806},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2008.10806v1},
}