@InProceedings{su-EtAl:2016:P16-1,
  author    = {Su, Pei-Hao  and  Gasic, Milica  and  Mrk\v{s}i\'{c}, Nikola  and  Rojas Barahona, Lina M.  and  Ultes, Stefan  and  Vandyke, David  and  Wen, Tsung-Hsien  and  Young, Steve},
  title     = {On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems},
  booktitle = {Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  month     = {August},
  year      = {2016},
  address   = {Berlin, Germany},
  publisher = {Association for Computational Linguistics},
  pages     = {2431--2441},
  url       = {http://www.aclweb.org/anthology/P16-1230}
}