@article{jotrajointtransformerandreinforcement,
  title = {JoTR: A Joint Transformer and Reinforcement Learning Framework for Dialog Policy Learning},
  author = {Wai-Chung Kwan and Huimin Wang and Hongru Wang and Zezhong Wang and Xian Wu and Yefeng Zheng and Kam-Fai Wong},
  year = {2023},
  eprint = {2309.00230},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2309.00230v1},
}