@article{dopldirectonlinepreferencelearningfor,
  title = {DOPL: Direct Online Preference Learning for Restless Bandits with Preference Feedback},
  author = {Guojun Xiong and Ujwal Dinesha and Debajoy Mukherjee and Jian Li and Srinivas Shakkottai},
  year = {2024},
  eprint = {2410.05527},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.05527v1},
}