@inproceedings{madusanka-etal-2020-dialog,
    title = "Dialog policy optimization for low resource setting using Self-play and Reward based Sampling",
    author = "Madusanka, Tharindu  and
      Langappuli, Durashi  and
      Welmilla, Thisara  and
      Thayasivam, Uthayasanker  and
      Jayasena, Sanath",
    editor = "Nguyen, Minh Le  and
      Luong, Mai Chi  and
      Song, Sanghoun",
    booktitle = "Proceedings of the 34th Pacific Asia Conference on Language, Information and Computation",
    month = oct,
    year = "2020",
    address = "Hanoi, Vietnam",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2020.paclic-1.21/",
    pages = "178--187"
}