Towards end-to-end learning for dialog state tracking and management using deep reinforcement learning

Codebase for Towards end-to-end learning for dialog state tracking and management using deep reinforcement learning, published as a long paper in SIGDIAL 2016. Reference information is in the end of this page. Presentation slides can be found here.

This work won the best paper nomination award at SIGDIAL 2016.

If you use any source codes or datasets included in this toolkit in your work, please cite the following paper. The bibtex are listed below:

@inproceedings{zhao2016towards,
  title={Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learning},
  author={Zhao, Tiancheng and Eskenazi, Maxine},
  booktitle={Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue},
  pages={1--10},
  year={2016}
}