@inproceedings{zhao-etal-2025-efficient,
    title = "An Efficient Task-Oriented Dialogue Policy: Evolutionary Reinforcement Learning Injected by Elite Individuals",
    author = "Zhao, Yangyang  and
      Niu, Ben  and
      Qin, Libo  and
      Wang, Shihan",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.acl-long.171/",
    pages = "3429--3442",
    ISBN = "979-8-89176-251-0"
}