@inproceedings{vath-vu-2019-combine,
    title = "To Combine or Not To Combine? A Rainbow Deep Reinforcement Learning Agent for Dialog Policies",
    author = {V{\"a}th, Dirk  and
      Vu, Ngoc Thang},
    editor = "Nakamura, Satoshi  and
      Gasic, Milica  and
      Zukerman, Ingrid  and
      Skantze, Gabriel  and
      Nakano, Mikio  and
      Papangelis, Alexandros  and
      Ultes, Stefan  and
      Yoshino, Koichiro",
    booktitle = "Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue",
    month = sep,
    year = "2019",
    address = "Stockholm, Sweden",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/W19-5908/",
    doi = "10.18653/v1/W19-5908",
    pages = "62--67",
    abstract = "In this paper, we explore state-of-the-art deep reinforcement learning methods for dialog policy training such as prioritized experience replay, double deep Q-Networks, dueling network architectures and distributional learning. Our main findings show that each individual method improves the rewards and the task success rate but combining these methods in a Rainbow agent, which performs best across tasks and environments, is a non-trivial task. We, therefore, provide insights about the influence of each method on the combination and how to combine them to form a Rainbow agent."
}