@article{learningkernelbasedmdpsfromepisodicprefe, title = {Learning Kernel-Based MDPs from Episodic Preferential Feedback}, author = {Nikola Pavlovic and Sattar Vakili and Qing Zhao}, year = {2026}, eprint = {2605.23650}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.23650}, }