@InProceedings{su-EtAl:2015:W15-46,
  author    = {Su, Pei-Hao  and  Vandyke, David  and  Gasic, Milica  and  Mrksic, Nikola  and  Wen, Tsung-Hsien  and  Young, Steve},
  title     = {Reward Shaping with Recurrent Neural Networks for Speeding up On-Line Policy Learning in Spoken Dialogue Systems},
  booktitle = {Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue},
  month     = {September},
  year      = {2015},
  address   = {Prague, Czech Republic},
  publisher = {Association for Computational Linguistics},
  pages     = {417--421},
  url       = {http://aclweb.org/anthology/W15-4655}
}