@article{rescueconversationsfromdeadendsefficient,
  title = {Rescue Conversations from Dead-ends: Efficient Exploration for Task-oriented Dialogue Policy Optimization},
  author = {Yangyang Zhao and Zhenyu Wang and Mehdi Dastani and Shihan Wang},
  year = {2023},
  eprint = {2305.03262},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2305.03262v1},
}