@article{anefficienttaskorienteddialoguepolicy,
  title = {An Efficient Task-Oriented Dialogue Policy: Evolutionary Reinforcement Learning Injected by Elite Individuals},
  author = {Yangyang Zhao and Ben Niu and Libo Qin and Shihan Wang},
  year = {2025},
  eprint = {2506.03519},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2506.03519v1},
}