Azran, G., Danesh, M. H., Albrecht, S. V., & Keren, S. (2024). Contextual Pre-planning on Reward Machine Abstractions for Enhanced Transfer in Deep Reinforcement Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 38(10), 10953–10961. https://doi.org/10.1609/aaai.v38i10.28970