Shangtong Zhang, Bo Liu, Hengshuai Yao, Shimon Whiteson. Provably Convergent Two-Timescale Off-Policy Actor-Critic with Function Approximation. In Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, Virtual Event. Volume 119 of Proceedings of Machine Learning Research, pages 11204-11213, PMLR, 2020. [doi]
@inproceedings{ZhangLYW20-0,
title = {Provably Convergent Two-Timescale Off-Policy Actor-Critic with Function Approximation},
author = {Shangtong Zhang and Bo Liu and Hengshuai Yao and Shimon Whiteson},
year = {2020},
url = {http://proceedings.mlr.press/v119/zhang20s.html},
researchr = {https://researchr.org/publication/ZhangLYW20-0},
cites = {0},
citedby = {0},
pages = {11204-11213},
booktitle = {Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, Virtual Event},
volume = {119},
series = {Proceedings of Machine Learning Research},
publisher = {PMLR},
}