@article{guideddialogpolicylearningwithout,
  title = {Guided Dialog Policy Learning without Adversarial Learning in the Loop},
  author = {Ziming Li and Sungjin Lee and Baolin Peng and Jinchao Li and Julia Kiseleva and Maarten de Rijke and Shahin Shayandeh and Jianfeng Gao},
  year = {2020},
  eprint = {2004.03267},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2004.03267v2},
}