UAI 2024poster20 citations

Towards Minimax Optimality of Model-based Robust Reinforcement Learning

Pierre Clavier, Erwan Le Pennec, Matthieu Geist

Abstract

We study the sample complexity of obtaining an $\epsilon$-optimal policy in

BibTeX
@InProceedings{pmlr-v244-clavier24a,
  title = 	 {Towards Minimax Optimality of Model-based Robust Reinforcement Learning},
  author =       {Clavier, Pierre and Le Pennec, Erwan and Geist, Matthieu},
  booktitle = 	 {Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence},
  pages = 	 {820--855},
  year = 	 {2024},
  editor = 	 {Kiyavash, Negar and Mooij, Joris M.},
  volume = 	 {244},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {15--19 Jul},
  publisher =    {PMLR},
  pdf = 	 {https://raw.githubusercontent.com/mlresearch/v244/main/assets/clavier24a/clavier24a.pdf},
  url = 	 {https://proceedings.mlr.press/v244/clavier24a.html},
  abstract = 	 {We study the sample complexity of obtaining an $\epsilon$-optimal policy in