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