Songtao Lu, Kaiqing Zhang, Tianyi Chen, Tamer Basar, Lior Horesh. Decentralized Policy Gradient Descent Ascent for Safe Multi-Agent Reinforcement Learning. 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 8767-8775, AAAI Press, 2021. [doi]
@inproceedings{LuZCBH21,
title = {Decentralized Policy Gradient Descent Ascent for Safe Multi-Agent Reinforcement Learning},
author = {Songtao Lu and Kaiqing Zhang and Tianyi Chen and Tamer Basar and Lior Horesh},
year = {2021},
url = {https://ojs.aaai.org/index.php/AAAI/article/view/17062},
researchr = {https://researchr.org/publication/LuZCBH21},
cites = {0},
citedby = {0},
pages = {8767-8775},
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},
}