@article{onpolicyreinforcementlearningwithentropy,
  title = {Policy Optimization Reinforcement Learning with Entropy Regularization},
  author = {Jingbin Liu and Xinyang Gu and Shuai Liu},
  year = {2019},
  eprint = {1912.01557},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1912.01557v3},
}