He J, Li K, Zang Y, Fu H, Fu Q, Xing J, et al. Not All Tasks Are Equally Difficult: Multi-Task Deep Reinforcement Learning with Dynamic Depth Routing. AAAI [Internet]. 2024 Mar. 24 [cited 2026 May 17];38(11):12376-84. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/29129