@inproceedings{guo-etal-2022-efficient,
    title = "Efficient (Soft) {Q}-Learning for Text Generation with Limited Good Data",
    author = "Guo, Han  and
      Tan, Bowen  and
      Liu, Zhengzhong  and
      Xing, Eric  and
      Hu, Zhiting",
    editor = "Goldberg, Yoav  and
      Kozareva, Zornitsa  and
      Zhang, Yue",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2022.findings-emnlp.518/",
    doi = "10.18653/v1/2022.findings-emnlp.518",
    pages = "6969--6991"
}