Neural-Network-Based Optimal Control for Discrete-Time Nonlinear Systems Using General Value Iteration

摘要：

In this paper, we propose a novel adaptive dynamic programming (ADP) scheme based on general value iteration to obtain near optimal control for discrete-time nonlinear systems with continuous state and control space. First, the selection of initial value function is different from the traditional value iteration, and a new method is introduced to demonstrate the convergence property and convergence speed of the value function. Then, the control law obtained at each iteration can stabilize the system under some conditions. At last, three neural networks with Levenberg-Marquardt training algorithm are used to approximate the unknown nonlinear system, the value function and the optimal control law. One simulation example is presented to demonstrate the effectiveness of the present scheme.

关键词： Adaptive dynamic programming approximate dynamic programming optimal control value iteration neural networks reinforcement learning

作者: LI Hongliang LIU Derong WANG Ding

作者单位: State Key Laboratory of Management and Control for Complex SystemsInstitute of Automation, Chinese A State Key Laboratory of Management and Control for Complex Systems Institute of Automation, Chinese

会议类型: 国际会议

会议名称: The 31st Chinese Control Conference(第三十一届中国控制会议)

会议地点: 合肥

会议语种:英文

页码: 2932-2937

在线出版日期: 2012-07-01（万方平台首次上网日期，不代表论文的发表时间）