@inproceedings{antioverestimationdialoguepolicylearning,
  title = {Anti-Overestimation Dialogue Policy Learning for Task-Completion Dialogue System},
  author = {Chang Tian and Wenpeng Yin and Marie-Francine Moens},
  year = {2022},
  booktitle = {Findings (NAACL) 2022 7},
  eprint = {2207.11762},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2207.11762v2},
}