arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.15350math.OCcs.SYeess.SY
收藏

Hamilton-Jacobi-Bellman方程稳定流形的深度神经网络逼近

Deep neural network approximations for the stable manifolds of the Hamilton-Jacobi-Bellman equations

Guoyuan Chen

AI总结:

本文证明逼近HJB方程稳定流形可产生稳定且近优的控制,并提出基于流形内随机轨迹自适应采样的无网格深度学习算法,用于高维非线性系统的最优反馈控制。

摘要:

对于一个无限时域控制问题,最优控制可以在半全局区域内由Hamilton-Jacobi-Bellman(HJB)方程的特征Hamilton系统的稳定流形表示。本文中,我们首先从理论上证明:如果一个逼近在某种意义上充分接近HJB方程的精确稳定流形,那么由该逼近导出的控制能够使系统稳定,并且接近最优。随后,基于这一理论结果,我们提出一种深度学习算法来逼近稳定流形,并数值计算最优反馈控制。该算法依赖于通过在稳定流形内随机寻找轨迹来自适应生成数据。此类算法基本上是无网格的,因此有可能应用于广泛的高维非线性系统。我们通过两个例子证明方法的有效性:稳定Reaction Wheel Pendulums(反作用轮摆)以及控制抛物型Allen-Cahn方程。

英文摘要:

For an infinite-horizon control problem, the optimal control can be represented by the stable manifold of the characteristic Hamiltonian system of Hamilton-Jacobi-Bellman (HJB) equation in a semiglobal domain. In this paper, we first theoretically prove that if an approximation is sufficiently close to the exact stable manifold of the HJB equation in a certain sense, then the control derived from this approximation stabilizes the system and is nearly optimal. Then, based on the theoretical result, we propose a deep learning algorithm to approximate the stable manifold and compute optimal feedback control numerically. The algorithm relies on adaptive data generation through finding trajectories randomly within the stable manifold. Such kind of algorithm is grid-free basically, making it potentially applicable to a wide range of high-dimensional nonlinear systems. We demonstrate the effectiveness of our method through two examples: stabilizing the Reaction Wheel Pendulums and controlling the parabolic Allen-Cahn equation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑