Wei H, Liu X, Ying L. A Provably-Efficient Model-Free Algorithm for Infinite-Horizon Average-Reward Constrained Markov Decision Processes. AAAI [Internet]. 2022 Jun. 28 [cited 2026 May 25];36(4):3868-76. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/20302