@article{fastratesforofflinecontextualbanditswith, title = {Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability}, author = {Qingyue Zhao and Kaixuan Ji and Heyang Zhao and Quanquan Gu}, year = {2026}, eprint = {2605.09214}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.09214}, }