Resilient reinforcement learning and robust output regulation under denial-of-service attacks
Resilient reinforcement learning and robust output regulation under denial-of-service attacks
复制标题
DOI：
10.1016/j.automatica.2022.110366
复制
发表时间：
2022-08
期刊：
影响因子：
--
通讯作者：
Weinan Gao;Chao Deng;Yi Jiang;Zhong-Ping Jiang
中科院分区：
文献类型：
--
作者：
Weinan Gao;Chao Deng;Yi Jiang;Zhong-Ping Jiang
在本文中，我们提出了一种新颖的弹性强化学习方法，用于解决动态不确定性和拒绝服务攻击下一类部分线性系统的鲁棒最优输出调节问题。与现有的强化学习工作有根本不同，所提出的方法严格分析了闭环系统抵御攻击的弹性和针对动态不确定性的鲁棒性。此外，我们提出了一种原始的逐次逼近方法，称为混合迭代，来学习鲁棒的最优控制策略，该策略比值迭代收敛得更快，并且独立于初始可接受的控制器。仿真结果证明了所提出方法的有效性。
In this paper, we have proposed a novel resilient reinforcement learning approach for solving robust optimal output regulation problems of a class of partially linear systems under both dynamic uncertainties and denial-of-service attacks. Fundamentally different from existing works on reinforcement learning, the proposed approach rigorously analyzes both the resilience of closed-loop systems against attacks and the robustness against dynamic uncertainties. Moreover, we have proposed an original successive approximation approach, named hybrid iteration, to learn the robust optimal control policy, that converges faster than value iteration, and is independent of an initial admissible controller. Simulation results demonstrate the efficacy of the proposed approach.