@article{onconvergenceofaveragerewardoffpolicy, title = {On Convergence of Average-Reward Off-Policy Control Algorithms in Weakly Communicating MDPs}, author = {Yi Wan and Richard S. Sutton}, year = {2022}, eprint = {2209.15141}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2209.15141v2}, }