Ouhamma R, Kamgarpour M. Learning in Zero-Sum Markov Games: Relaxing Strong Reachability and Mixing Time Assumptions. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 14];40(20):17170-8. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/38767