@inproceedings{su-etal-2015-reward,
    title = "Reward Shaping with Recurrent Neural Networks for Speeding up On-Line Policy Learning in Spoken Dialogue Systems",
    author = "Su, Pei-Hao  and
      Vandyke, David  and
      Ga{\v{s}}i{\'c}, Milica  and
      Mrk{\v{s}}i{\'c}, Nikola  and
      Wen, Tsung-Hsien  and
      Young, Steve",
    editor = "Koller, Alexander  and
      Skantze, Gabriel  and
      Jurcicek, Filip  and
      Araki, Masahiro  and
      Rose, Carolyn Penstein",
    booktitle = "Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
    month = sep,
    year = "2015",
    address = "Prague, Czech Republic",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/W15-4655/",
    doi = "10.18653/v1/W15-4655",
    pages = "417--421"
}