@article{reinforcementlearningwithpairwiseprefere, title = {Reinforcement Learning with Pairwise Preferences in Long-Term Decision Problems}, author = {Jonathan Colaço Carr and Prakash Panangaden and Doina Precup and Benjamin Van Roy}, year = {2026}, eprint = {2606.00367}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.00367}, }