Wang M, Li X, Wang M, Bennis H. Offline Meta-Reinforcement Learning with Flow-Based Task Inference and Adaptive Correction of Feature Overgeneralization. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 17];40(31):26390-7. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/39845