姓名：倪元华

性别：男

所属部门：自动化系

行政职务：

职称：教授

学历：博士

所学专业：

办公电话：

电子邮件：yhni@nankai.edu.cn

研究方向：强化学习、最优控制、运筹学与最优化

教授，博士生导师，主要教育/工作经历如下:

2010年7月，于中国科公司数学与系统科学研究院获博士学位

2013年6月-2017年1月，中国科公司系统科学研究所，博士后

2014年5月-2015年5月，美国加州大学（圣地亚哥），访问学者

2016年5月-2017年1月，香港理工大学，博士后

2017年1月-至今，betway88西汉姆联

研究兴趣：

本课题组以“数据”与“决策”为研究主体，围绕强化学习、最优控制、运筹学与最优化、智能博弈等领域的交叉融合与应用，一方面，关注这几个学科内生的基本性问题，以系统学的观点探讨融通共进的一般性理论，另一方面，开展问题驱动的数据科学与决策科学研究，比如群体智能、智能博弈、优化调度、基于机器学习的优化等。

                                                           “Reinforcement Learning is Direct Adaptive Optimal Control”

                                                                                                      ———R. S. Sutton, A. G. Barto, R. J. Williams

                                                                                                                 IEEE Control Systems Magazine, 1992 pdf

R. S. Sutton和A. G. Barto是2024年图灵奖得主；强化学习与最优控制具有天然内在关联，二者均以序贯决策的性能优化为核心目标，却分属数据驱动与模型驱动范式，而优化方法正是衔接二者的关键技术内核，并为策略学习与控制性能提升提供重要理论和方法支撑。

2026、2027年，本科生实习、研究生招生重点方向：强化学习、大模型决策

要求：做事积极主动、工作热忱饱满，具备出色的团队协作能力；对强化学习、智能控制与决策等方向有浓厚科研兴趣；具备扎实的编程能力（Python/Matlab 等）

期刊编委：

 1. System & Control Letters，Associate Editor

 2. IEEE Control Systems Letters,  Associate Editor

员工培养：部分讨论班笔记如下

1. 优化笔记：《Lectures on Convex Optimization》(I) pdf ,   《First­ Order Methods in Optimization》(I) pdf  (II)  pdf 

2. 强化学习经典论文研读：(I) pdf

招生说明：

1.  在人工智能、控制科学与工程、运筹学与控制论等方向上招收硕士生、博士生；

2.  招生要求：长期主义，做事踏实；

3.  感兴趣的同学可直接发邮件联系我；

4.  参考阅读：

如何成为一名优秀的博士生？（链接：http://carbon.dlut.edu.cn/info/1054/1102.htm）

身心自在《学者笔谈》（链接：http://emba.sjtu.edu.cn/news/media/ZHEMBA4280.html ）

https://mp.weixin.qq.com/s/Ye3-72rB_TIUvCQxoIK9_g

代表性论文 (研究生#，通讯作者*)：                                           

[49]Jun Xie#, Yuan-Hua Ni*, Yiqin Yang, and Bo Xu, Data-enabled policy and value iteration for continuous-time linear quadratic output feedback control, arXiv:2603.14386.

[48]Yiqin Yang, Xu Yang, Yuhua Jiang, Ni Mu, Hao Hu, Runpeng Xie, Ziyou Zhang, Siyuan Li, Yuan-Hua Ni, Qianchuan Zhao, and Bo Xu, GlobeDiff: State diffusion process for partial observability in multi-agent systems, arXiv:2602.15776.

[47]Hui Jia#, Yuan-Hua Ni*, and Guangchen Wang, Stabilizing rate of stochastic control systems, arXiv:2512.06349.

[46]Jun Xie#, Yuan-Hua Ni*, Yiqin Yang*, and Bo Xu, An efficient data-driven framework for linear quadratic output feedback control,  arXiv:2508.20748.

[45]Haoran Li#, Xun Li, Yuan-Hua Ni*, and Xuebo Zhang, Policy optimization in the linear quadratic gaussian problem: A frequency domain perspective,  arXiv:2508.17252.

[44]Meiling Yu#, Lechen Feng#, Lei Jiang,  and Yuan-Hua Ni*, A Convex optimization approach to model-free inverse optimal control with provable convergence, arXiv:2507.19965.

[43] Lechen Feng#, Xun Li,  and Yuan-Hua Ni*, Nonconvex optimization framework for group-sparse feedback linear-quadratic optimal control: Non-penalty approach, arXiv:2507.19895.    

[42]Lechen Feng#, Xun Li and Yuan-Hua Ni*, Nonconvex optimization framework for group-sparse feedback linear-quadratic optimal control: Penalty approach, arXiv:2507.18114.

[41]Haotian Tan# and Yuan-Hua Ni*, A high-speed time-optimal trajectory generation strategy via a two-layer planning model, arXiv:2503.11072.

[40]Yutian Wang#, Yuan-Hua Ni*, and Xun Li, An optimization-based framework for solving forward-backward stochastic differential equations: Convergence analysis and error bounds, arXiv:2507.15234.

[39]Ruru Jia#, Yuan-Hua Ni, Cong Bi*, and Gang Feng, Cooperative output regulation of heterogeneous linear stochastic multi-agent systems, to apperar in Automatica. (Regular Paper)

[38]]Ruru Jia#, Yuan-Hua Ni*, and Guangchen Wang, Event-triggered global and group consensus for linear multiagent systems with multiplicative noises, Automatica, 2026, 183: 112595. (Regular Paper) 

[37]Ruru Jia#, Xiaofeng Zong, and Yuan-Hua Ni*, Distributed event-triggered time-varying formation control under multiplicative noises, International Journal of Robust and Nonlinear Control, 2025, 35: 5782-5796.

[36]Zhen Zhang#, Qingsheng Li# and Yuan-Hua Ni*, Differentially private distributed nash equilibrium seeking based on gradient tracking and communication compression, Systems & Control Letters, 2025, 204: 106217.

[35]Zhen Zhang# and Yuan-Hua Ni*, Gradient tracking for sum-of-nonconvex decentralized optimization, International Journal of Robust and Nonlinear Control, 2025, 35:5238-5245.

[34]Lechen Feng# and Yuan-Hua Ni*, Analysis of linear-quadratic optimal control via a hybrid control lens, Asian Journal of Control, 2025, 27: 1914-1925.

[33]Haoran Li# and Yuan-Hua Ni*, Policy optimization of finite-horizon Kalman filter with unknown noise covariance, Automatica, 2025, 177: 112320. (Regular Paper)

[32]Qingsheng Li#, Hui Jia#, and Yuan-Hua Ni*, Turnpike properties of pareto efficient in cooperative linear-quadratic differential games, The 14th Asian Control Conference, 2024, July. (Best Student Paper Award Finalist)

[31]Lechen Feng# and Yuan-Hua Ni*, Accelerated optimization landscape of linear-quadratic regulator, Automatica, 2025, 171: 111927. 

 

[30]Hui Jia# and Yuan-Hua Ni*, Decentralized stochastic linear-quadratic optimal control with risk constraint and partial observation, System & Control Letters, 2024, 187:105778. 

[29]Yutian Wang#, Yuan-Hua Ni*, Zengqiang Chen, and Ji-Feng Zhang, Probabilistic framework of Howard‘s policy iteration: BML evaluation and robust convergence analysis, IEEE Transactions on Automatic Control,  2026, 69(8): 5200-5215. (Full Paper)  

[28]Hui Jia# and Yuan-Hua Ni*, Partially observed optimal control of local and remote controllers, International Journal of Robust and Nonlinear Control, 2024, 34: 3189-3206. 

[27]Di. Zhang# and Yuan-Hua Ni*, Differential privacy optimal control with asymmetric information structure, Optimal Control Applications and Methods, 2024, 45: 393-412. 

[26]Yuan-Hua Ni, Liping Liu, and Xinzhen Zhang, Deterministic dynamic Stackelberg games: time-consistent open-loop solution, Automatica, 2023, 148: 110757. (Regular Paper) 

[25]Yuan-Hua Ni, Binbin Si, and Xinzhen Zhang, A Nash-type fictitious game framework to time-inconsistent stochastic control problems, SIAM Journal on Control and Optimization, 2022, 60(2): 1163-1189. 

[24]Hongyuan Xu#, Yuan-Hua Ni*, Zhongxin Liu, and Zengqiang Chen,Privacy-preserving leader-following consensus via node-augment mechanism, IEEE Transactions on Circuits and Systems II: Express Briefs, 2021, 68(6): 2117-2121.

[23]Binbin Si#, Yuan-Hua Ni*, Qinglin Sun, and Zengqiang Chen, A robust time-inconsistent linear-quadratic problem. International Journal of Robust and Nonlinear Control, 2021, 31(7): 2737-2761.

[22]Binbin Si#,Yuan-Hua Ni*, Ji-Feng Zhang, Time-inconsistent stochastic LQ problem with regime switching, Journal of Systems Science and Complexity, 2020, 33: 1733-754. 

   

[21]Fuyong Wang, Yuan-Hua Ni, Zhongxin Liu, Zengqiang Chen. Fully distributed containment control for second-order multi-agent systems with communication delay. ISA Transactions, 2020, 99: 123-129.             

         

[20]Yuan-Hua Ni, Xun Li, Ji-Feng Zhang and Miroslav Krstic, Equilibrium solutions of multi-period mean-variance portfolio selection, IEEE Transactions on Automatic Control, 2020, 65(4): 1716-1723.        

                                

[19]Fu-Yong Wang, Yuan-Hua Ni, Zhong-Xin Liu, and Zeng-Qiang Chen, Containment control for general second-order multiagent systems with switched dynamics, IEEE Transactions on Cybernetics, 2020, 50(2): 550-560.     

                               

[18]Bing-Chang Wang, Yuan-Hua Ni*, Huanshui Zhang, Mean field games for multi-agents systems with multiplicative noises, International Journal of Robust and Nonlinear Control, 2019, online, DOI: 10.1002/rnc.4719. 

     

[17]Yuan-Hua Ni, Xun Li, Ji-Feng Zhang and Miroslav Krstic, Mixed equilibrium solution of time-inconsistent stochastic LQ problem, SIAM Journal on Control and Optimization, 2019, vol.57, no.1, pp.533-569.    

                                                          

[16]Yuan-Hua Ni, Ji-Feng Zhang, Miroslav Krstic, Time-inconsistent mean-field stochastic LQ problem: open-loop time-consistent control, IEEE Transactions on Automatic Control, 2018, 63(9): 2771-2786.  (Full Paper)  

                                              

[15]Yuan-Hua Ni, Cedric Ka-Fai Yiu, Huanshui Zhang and Ji-Feng Zhang, Delayed optimal control of stochastic LQ problem, SIAM Journal on Control and Optimization, 2017, 55(5): 3370-3407.             

                                   

[14]Yuan-Hua Ni, Xun Li, Ji-Feng Zhang, Indefinite mean-field stochastic linear-quadratic optimal control: from finite horizon to infinite horizon, IEEE Transactions on Automatic Control, 2016, 61 (11): 3269-3284. (Full Paper)   

                             

[13]Yuan-Hua Ni, Xun Li, Ji-Feng Zhang, Mean-field stochastic linear-quadratic optimal control with Markov jump parameters, System & Control Letter, 2016, 93：69-76.

[12]Wei Ni, Dongya Zhao, Yuanhua Ni, Xiaoli Wang, Stochastic averaging approach to leader-following consensus of linear multi-agent systems, Journal of the Franklin Institute, 2016, 353 (12): 2650-2669.                                        

        

[11]Yuan-Hua Ni, Ji-Feng Zhang, Stochastic linear-quadratic optimal control without time-consistency requirement, Communications in Information and Systems, 2015, 15 (4): 521-550.  

          

[10]Yuan-Hua Ni, Ji-Feng Zhang, Xun Li, Indefinite mean-field stochastic linear-quadratic optimal control, IEEE Transactions on Automatic Control, 2015, 60 (7): 1786-1800. (Full Paper)  

    

[9] Yuan-Hua Ni, Robert Elliott, Xun Li, Discrete-time mean-field stochastic linear- quadratic optimal control problems. II---infinite horizon case, Automatica, 2015, 57: 65-77. (Regular Paper) 

 

[8] Wan-Kai Pang, Yuan-Hua Ni, Xun Li, Ka-Fai Cedric Yiu, Continuous-time mean-variance portfolio selection with partial information, Journal of Mathematical Finance, 2014, 4: 353-365.

[7] Yuan-Hua Ni, Hai-Tao Fang, Policy iteration algorithm for controlled singular diffusion processes, SIAM Journal on Control and Optimization, 2013, 51 (5): 3844-3862.  

[6] Robert Elliott, Xun Li, Yuan-Hua Ni*, Discrete time mean-field stochastic linear-quadratic optimal control problems, Automatica, 2013, 49 (11): 3222-3233. (Regular Paper) 

 

[5] Yuan-Hua Ni, Xun Li, Consensus seeking in multi-agent systems with multiplicative measurement noises, Systems & Control Letters, 2013, 62 (5): 430-437.

[4] Yuan-Hua Ni, Output feedback H-infinity control for a class of nonlinear stochastic systems, Acta Mathematicae Applicatae Sinica, English Series, 2010, 26 (2): 251-266.

[3] Yuan-Hua Ni, Weihai Zhang, Hai-Tao Fang, On the observability and detectability of linear stochastic systems with Markov jumps and multiplicative noise, Journal of Systems Science and Complexity, 2010, 23 (1): 102-115.

[2] 倪元华, 桂克锋, 基于奇异摄动理论的电驱动机器人神经网络控制, 工程数学学报, 2007, 24 (2): 204-208.       

       

[1] 彭济根, 倪元华, 乔红, 柔性关节机械手的神经网络控制, 自动化学报, 2007, 33 (2): 175-180.