@article{adaptivediscretizationbasednonepisodic,
  title = {Policy Zooming: Adaptive Discretization-based Infinite-Horizon Average-Reward Reinforcement Learning},
  author = {Avik Kar and Rahul Singh},
  year = {2024},
  eprint = {2405.18793},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2405.18793v3},
}