Page 185 - 《软件学报》2021年第11期

陈子璇 等:一种基于广义异步值迭代的规划网络模型 3511

[21] van Hasselt H. Double Q-learning. In: Proc. of the Advances in Neural Information Processing Systems (NIPS). 2016. 2613−2621.
[22] van Hasselt H, Guez A, Silver D. Deep reinforcement learning with double Q-learning. In: Proc. of the AAAI Conf. on Artificial
Intelligence (AAAI). 2016. 2094−2100.
[23] Defferrard M, Bresson X, Vandergheynst P. Convolutional neural networks on graphs with fast localized spectral filtering. In: Proc.
of the Advances in Neural Information Processing Systems (NIPS). 2016. 3837−3845.
[24] Niepert M, Ahmed M, Kutzkov K. Learning convolutional neural networks for graphs. In: Proc. of the Int’l Conf. on Machine
Learning (ICML). 2016. 2014−2023.
[25] Franceschi L, Niepert M, Pontil M, He X. Learning discrete structures for graph neural networks. In: Proc. of the Int’l Conf. on
Machine Learning (ICML). 2019. 1972−1982.

附中文参考文献:
[1] 孙志军,薛磊,许阳明,王正,深度学习研究综述.计算机应用研究,2012,29(8):2806−2810.
[2] 刘全,翟建伟,章宗长,钟珊,周倩,章鹏,徐进.深度强化学习综述.计算机学报,2018,41(1):1−27.

陈子璇(1996－),女,博士生,CCF 学生会 潘致远(1993－),男,硕士,主要研究领域为
员,主要研究领域为强化学习,智能规划. 强化学习.

章宗长(1985－),男,博士,副教授,CCF 高 张琳婧(1995－),女,硕士,主要研究领域为
级会员,主要研究领域为强化学习,智能规 强化学习.
划,多智能体系统.