@article{orderoptimalinstancedependentboundsfor, title = {Order-Optimal Instance-Dependent Bounds for Offline Reinforcement Learning with Preference Feedback}, author = {Zhirui Chen and Vincent Y. F. Tan}, year = {2024}, eprint = {2406.12205}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.12205v1}, }