Adaptive Critic Designs for Discrete-Time Zero-Sum Games With Application to $H_{\infty}$ Control
Adaptive Critic Designs for Discrete-Time Zero-Sum Games With Application to $H_{\infty}$ Control
复制标题
DOI：
10.1109/tsmcb.2006.880135
复制
发表时间：
2007-02
期刊：
影响因子：
--
通讯作者：
A. Al-Tamimi;M. Abu-Khalaf;F. Lewis
中科院分区：
文献类型：
--
作者：
A. Al-Tamimi;M. Abu-Khalaf;F. Lewis
在这种对应关系中，自适应批评近似动态规划设计，推导出解决离散时间零和游戏的状态和动作空间是连续的。这导致了一个时间向前的强化学习算法，收敛到相应的零和游戏的纳什均衡。在这个对应的结果可以被认为是一种方法来解决著名的离散时间Hinfin最优控制问题的Riccati方程的时间向前。提出了两种方案，即：1）启发式动态规划和2）双重启发式动态规划，分别解决价值函数和对策的状态，。以F-16飞机的Hinfin自动驾驶仪设计为例说明了结果
In this correspondence, adaptive critic approximate dynamic programming designs are derived to solve the discrete-time zero-sum game in which the state and action spaces are continuous. This results in a forward-in-time reinforcement learning algorithm that converges to the Nash equilibrium of the corresponding zero-sum game. The results in this correspondence can be thought of as a way to solve the Riccati equation of the well-known discrete-time Hinfin optimal control problem forward in time. Two schemes are presented, namely: 1) a heuristic dynamic programming and 2) a dual-heuristic dynamic programming, to solve for the value function and the costate of the game, respectively. An Hinfin autopilot design for an F-16 aircraft is presented to illustrate the results