@article{optimalpolicyevaluationusingkernelbased, title = {Optimal policy evaluation using kernel-based temporal difference methods}, author = {Yaqi Duan and Mengdi Wang and Martin J. Wainwright}, year = {2021}, eprint = {2109.12002}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2109.12002v1}, }