@inproceedings{su-etal-2017-sample,
    title = "Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management",
    author = "Su, Pei-Hao  and
      Budzianowski, Pawe{\l}  and
      Ultes, Stefan  and
      Ga{\v{s}}i{\'c}, Milica  and
      Young, Steve",
    editor = "Jokinen, Kristiina  and
      Stede, Manfred  and
      DeVault, David  and
      Louis, Annie",
    booktitle = "Proceedings of the 18th Annual {SIG}dial Meeting on Discourse and Dialogue",
    month = aug,
    year = "2017",
    address = {Saarbr{\"u}cken, Germany},
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/W17-5518/",
    doi = "10.18653/v1/W17-5518",
    pages = "147--157"
}