@inproceedings{ijcai2011p314,
  title     = {Sample Efficient On-Line Learning of Optimal Dialogue Policies with Kalman Temporal Differences},
  author    = {Pietquin, Olivier and Geist, Matthieu and Chandramohan, Senthilkumar},
  booktitle = {Proceedings of the Twenty-Second International Joint Conference on
               Artificial Intelligence, {IJCAI-11}},
  publisher = {AAAI Press/International Joint Conferences on Artificial Intelligence},
  editor    = {Toby Walsh},
  pages     = {1878--1882},
  year      = {2011},
  month     = {7},
  doi       = {10.5591/978-1-57735-516-8/IJCAI11-314},
  url       = {https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-314},
}