Value Iteration Adaptive Dynamic Programming for Optimal Control of Discrete-Time Nonlinear Systems
ValueIterationAdaptiveDynamicProgrammingforOptimalControlofDiscrete-TimeNonlinearSystems,2016.QinglaiWei,Member,IEEE,DerongLiu,Fellow,IEEE,andHanquanLin对离散时间非线性系统,采用值迭代ADP算法,求解无限时域无折扣因子最优控制问题。初始值函数为任意