@inproceedings{tian-etal-2022-anti,
    title = "Anti-Overestimation Dialogue Policy Learning for Task-Completion Dialogue System",
    author = "Tian, Chang  and
      Yin, Wenpeng  and
      Moens, Marie-Francine",
    editor = "Carpuat, Marine  and
      de Marneffe, Marie-Catherine  and
      Meza Ruiz, Ivan Vladimir",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2022",
    month = jul,
    year = "2022",
    address = "Seattle, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.findings-naacl.43/",
    doi = "10.18653/v1/2022.findings-naacl.43",
    pages = "565--577"
}