论文标题
通过深神经网络近似对自主系统的半光彩最佳反馈稳定
Semiglobal optimal feedback stabilization of autonomous systems via deep neural network approximation
论文作者
论文摘要
提出并分析了一种非线性连续时间控制系统最佳反馈收益的学习方法。目的是建立一个严格的框架，用于计算使用神经网络近似最佳反馈收益的框架。该方法基于两种主要成分。首先，一种最佳控制公式，涉及反馈增益功能给出的“控制”变量的轨迹集合。其次，通过实现神经网络的反馈函数近似。基于通用近似属性，我们证明了最佳稳定神经网络反馈控制器的存在和收敛性。
A learning approach for optimal feedback gains for nonlinear continuous time control systems is proposed and analysed. The goal is to establish a rigorous framework for computing approximating optimal feedback gains using neural networks. The approach rests on two main ingredients. First, an optimal control formulation involving an ensemble of trajectories with 'control' variables given by the feedback gain functions. Second, an approximation to the feedback functions via realizations of neural networks. Based on universal approximation properties we prove the existence and convergence of optimal stabilizing neural network feedback controllers.
