@article{reinforcementlearningforfinitehorizon,
  title = {Reinforcement Learning for Finite-Horizon Restless Multi-Armed Multi-Action Bandits},
  author = {Guojun Xiong and Jian Li and Rahul Singh},
  year = {2021},
  eprint = {2109.09855},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2109.09855v2},
}