[1] Chunyuan Zhang, Chao Liu, Qi Song, Jie Zhao. Recursive Least Squares Policy Control with Echo State Network[C]. 4th International Conference on Artificial Intelligence and Big Data, PP.104-108, 2021.

[2] Chunyuan Zhang, Chao Liu, Jie Zhao. Efficient mini-batch training for echo state networks[C].Proceedings of 2020 6th International Conference on Robotics and Artificial Intelligence，PP.239-243,2020.

[3]赵杰,张春元*,刘超,周辉,欧宜贵,宋淇.递归最小二乘循环神经网络[J/OL].自动化学报:1-12, 2020.

[4] Hongyao Deng, Jinsong Tao, Xiuli Song, Chunyuan Zhang. Estimation of the Parameters of a Weighted Nuclear Norm Model and its Application in Image Denoising[J]. Information Sciences, Vol.528, PP.246-264, 2020.

[5] Chunyuan Zhang, Qingxin Zhu, Xinzheng Niu. Multikernel Recursive Least-Squares Temporal Difference Learning[C]. 12th International Conference on Intelligent Computing, Vol.9773, PP.205-217, 2016.

[6] Chunyuan Zhang, Qingxin Zhu, Yigui Ou and Xinzheng Niu. Actor-Critic Algorithms withϵ-Greedy Gaussian Policy in Multidimensional Continuous Action Spaces[J]. International Journal of Innovative Computing, Information and Control, Vol.12, No.3, June, PP.941-957, 2016.

[7] Chunyuan Zhang, Qingxin Zhu, Xinzheng Niu. Kernel Recursive Least-Squares Temporal Difference Algorithms with Sparsification and Regularization[J]. Computational Intelligence and Neuroscience, 2016:2305854, epub Jun 29, 2016.

[8]张春元,朱清新.基于对称扰动采样的Actor-critic算法[J].控制与决策, 2015, 30(12): 2161-2167.

[9] 张春元,朱清新,钟声. 连续空间增量最近邻时域差分学习[J]. 控制与决策, 2014, 29(12): 2121-2128.