Yuqian Jiang, Suda Bharadwaj, Bo Wu 0005, Rishi Shah, Ufuk Topcu, Peter Stone. Temporal-Logic-Based Reward Shaping for Continuing Reinforcement Learning Tasks. In Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, February 2-9, 2021. pages 7995-8003, AAAI Press, 2021. [doi]
Abstract is missing.