@article{qmmroffpolicyevaluationviarecursiverewei, title = {Q-MMR: Off-Policy Evaluation via Recursive Reweighting and Moment Matching}, author = {Xiang Li and Nan Jiang}, year = {2026}, eprint = {2605.06474}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.06474}, }