@InProceedings{suhr-artzi:2018:Long,
  author    = {Suhr, Alane  and  Artzi, Yoav},
  title     = {Situated Mapping of Sequential Instructions to Actions with Single-step Reward Observation},
  booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  month     = {July},
  year      = {2018},
  address   = {Melbourne, Australia},
  publisher = {Association for Computational Linguistics},
  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.},
  url       = {http://www.aclweb.org/anthology/P18-1193}
}