He Z, Qiao P, Li R, Dou Y, Tan Y. Highly Parallelized Reinforcement Learning Training with Relaxed Assignment Dependencies. AAAI [Internet]. 2025 Apr. 11 [cited 2026 May 13];39(16):17159-67. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/33886