基于值迭代的自适应动态规划的收敛条件

摘要

The convergence condition of value-iteration based adaptive dynamic programming which is applied to discrete time nonlinear non-affine system is studied. Convergence of value-iteration based adaptive dynamic programming is proven. The proof shows that value iteration will converge to the optimal when the initial iterative performance index function is a positive semi-definite function.%研究了应用于离散时间非仿射非线性系统的基于值迭代的自适应动态规划的收敛条件, 指出了迭代性能指标函数初始化为半正定函数可保证值迭代收敛到最优, 并给出了证明.