@article{neuralduelingbandits,
  title = {Neural Dueling Bandits: Preference-Based Optimization with Human Feedback},
  author = {Arun Verma and Zhongxiang Dai and Xiaoqiang Lin and Patrick Jaillet and Bryan Kian Hsiang Low},
  year = {2024},
  eprint = {2407.17112},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.17112v2},
}