Qichao Zhang, Dongbin Zhao, Sibo Zhang. Off-Policy Reinforcement Learning for Partially Unknown Nonzero-Sum Games. In Derong Liu, Shengli Xie, Yuanqing Li, Dongbin Zhao, El-Sayed M. El-Alfy, editors, Neural Information Processing - 24th International Conference, ICONIP 2017, Guangzhou, China, November 14-18, 2017, Proceedings, Part I. Volume 10634 of Lecture Notes in Computer Science, pages 822-830, Springer, 2017. [doi]
@inproceedings{ZhangZZ17-18, title = {Off-Policy Reinforcement Learning for Partially Unknown Nonzero-Sum Games}, author = {Qichao Zhang and Dongbin Zhao and Sibo Zhang}, year = {2017}, doi = {10.1007/978-3-319-70087-8_84}, url = {https://doi.org/10.1007/978-3-319-70087-8_84}, researchr = {https://researchr.org/publication/ZhangZZ17-18}, cites = {0}, citedby = {0}, pages = {822-830}, booktitle = {Neural Information Processing - 24th International Conference, ICONIP 2017, Guangzhou, China, November 14-18, 2017, Proceedings, Part I}, editor = {Derong Liu and Shengli Xie and Yuanqing Li and Dongbin Zhao and El-Sayed M. El-Alfy}, volume = {10634}, series = {Lecture Notes in Computer Science}, publisher = {Springer}, isbn = {978-3-319-70087-8}, }