@article{almostsureconvergenceofdifferentialtempo, title = {Almost Sure Convergence of Differential Temporal Difference Learning for Average Reward Markov Decision Processes}, author = {Ethan Blaser and Jiuqi Wang and Shangtong Zhang}, year = {2026}, eprint = {2602.16629}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.16629}, }