@article{klentropyregularizedrlwithagenerative,
  title = {KL-Entropy-Regularized RL with a Generative Model is Minimax Optimal},
  author = {Tadashi Kozuno and Wenhao Yang and Nino Vieillard and Toshinori Kitamura and Yunhao Tang and Jincheng Mei and Pierre Ménard and Mohammad Gheshlaghi Azar and Michal Valko and Rémi Munos and Olivier Pietquin and Matthieu Geist and Csaba Szepesvári},
  year = {2022},
  eprint = {2205.14211},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2205.14211v1},
}