@article{valuefunctionestimationinmarkovreward,
  title = {Instance-dependent $\ell_\infty$-bounds for policy evaluation in tabular reinforcement learning},
  author = {Ashwin Pananjady and Martin J. Wainwright},
  year = {2019},
  eprint = {1909.08749},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1909.08749v2},
}