@article{averagerewardoffpolicypolicyevaluation, title = {Average-Reward Off-Policy Policy Evaluation with Function Approximation}, author = {Shangtong Zhang and Yi Wan and Richard S. Sutton and Shimon Whiteson}, year = {2021}, eprint = {2101.02808}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2101.02808v3}, }