@inproceedings{takanobu-etal-2020-multi,
    title = "Multi-Agent Task-Oriented Dialog Policy Learning with Role-Aware Reward Decomposition",
    author = "Takanobu, Ryuichi  and
      Liang, Runze  and
      Huang, Minlie",
    editor = "Jurafsky, Dan  and
      Chai, Joyce  and
      Schluter, Natalie  and
      Tetreault, Joel",
    booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
    month = jul,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2020.acl-main.59/",
    doi = "10.18653/v1/2020.acl-main.59",
    pages = "625--638"
}