@article{nonlinearreinforcementlearninginlarge,
  title = {Non-Linear Reinforcement Learning in Large Action Spaces: Structural Conditions and Sample-efficiency of Posterior Sampling},
  author = {Alekh Agarwal and Tong Zhang},
  year = {2022},
  eprint = {2203.08248},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2203.08248v2},
}