@inproceedings{suhr-artzi-2018-situated,
    title = "Situated Mapping of Sequential Instructions to Actions with Single-step Reward Observation",
    author = "Suhr, Alane  and
      Artzi, Yoav",
    editor = "Gurevych, Iryna  and
      Miyao, Yusuke",
    booktitle = "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2018",
    address = "Melbourne, Australia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/P18-1193/",
    doi = "10.18653/v1/P18-1193",
    pages = "2072--2082",
    abstract = "We propose a learning approach for mapping context-dependent sequential instructions to actions. We address the problem of discourse and state dependencies with an attention-based model that considers both the history of the interaction and the state of the world. To train from start and goal states without access to demonstrations, we propose SESTRA, a learning algorithm that takes advantage of single-step reward observations and immediate expected reward maximization. We evaluate on the SCONE domains, and show absolute accuracy improvements of 9.8{\%}-25.3{\%} across the domains over approaches that use high-level logical representations."
}