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]
@inproceedings{JiangB0STS21,
title = {Temporal-Logic-Based Reward Shaping for Continuing Reinforcement Learning Tasks},
author = {Yuqian Jiang and Suda Bharadwaj and Bo Wu 0005 and Rishi Shah and Ufuk Topcu and Peter Stone},
year = {2021},
url = {https://ojs.aaai.org/index.php/AAAI/article/view/16975},
researchr = {https://researchr.org/publication/JiangB0STS21},
cites = {0},
citedby = {0},
pages = {7995-8003},
booktitle = {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},
publisher = {AAAI Press},
isbn = {978-1-57735-866-4},
}