Jiang, Y., S. Bharadwaj, B. Wu, R. Shah, U. Topcu, and P. Stone. “Temporal-Logic-Based Reward Shaping for Continuing Reinforcement Learning Tasks”. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 9, May 2021, pp. 7995-03, doi:10.1609/aaai.v35i9.16975.