Azran G, Danesh MH, Albrecht SV, Keren S. Contextual Pre-planning on Reward Machine Abstractions for Enhanced Transfer in Deep Reinforcement Learning. AAAI [Internet]. 2024 Mar. 24 [cited 2026 May 19];38(10):10953-61. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/28970