@article{reinforcementlearningandbanditsforspeech,
  title = {Reinforcement Learning and Bandits for Speech and Language Processing: Tutorial, Review and Outlook},
  author = {Baihan Lin},
  year = {2022},
  eprint = {2210.13623},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2210.13623v3},
}