arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2312.09310math.OCcs.AI
收藏

神经时间反转广义Riccati方程

Neural Time-Reversed Generalized Riccati Equation

University of Siena(锡耶纳大学);University of Florence(佛罗伦萨大学)

Alessandro Betti, Michele Casoni, Marco Gori, Simone Marullo, Stefano Melacci, Matteo Tiezzi

AI总结:

针对最优控制中哈密顿方程依赖全时域前后向算法的问题,提出基于神经网络的前向时间最优控制方法,用时间反转广义Riccati方程更新协态估计网络参数,推测其可稳定状态动力学并通过实验验证。

摘要:

最优控制处理的是变量引导动力系统、且系统结果影响目标函数的优化问题。求解这类问题的两种经典方法是动态规划和庞特里亚金极大值原理。在这两种方法中,哈密顿方程通过被称为协态的辅助变量给出了最优性的一种解释,但由于依赖整个时间域上的前向-后向算法,哈密顿方程很少被使用。本文提出了一种新颖的基于神经网络的最优控制方法,旨在实现时间前向运行。神经网络不仅被用于实现状态动力学,还被用于估计协态变量。后者网络的参数在每个时间步通过一种新提出的局部策略——即时间反转广义Riccati方程——来确定。该策略的灵感来自线性二次(LQ)问题中讨论的一个结果,我们推测该结果能稳定状态动力学。我们通过讨论一系列最优控制案例研究的实验结果来支持这一推测。

英文摘要:

Optimal control deals with optimization problems in which variables steer a dynamical system, and its outcome contributes to the objective function. Two classical approaches to solving these problems are Dynamic Programming and the Pontryagin Maximum Principle. In both approaches, Hamiltonian equations offer an interpretation of optimality through auxiliary variables known as costates. However, Hamiltonian equations are rarely used due to their reliance on forward-backward algorithms across the entire temporal domain. This paper introduces a novel neural-based approach to optimal control, with the aim of working forward-in-time. Neural networks are employed not only for implementing state dynamics but also for estimating costate variables. The parameters of the latter network are determined at each time step using a newly introduced local policy referred to as the time-reversed generalized Riccati equation. This policy is inspired by a result discussed in the Linear Quadratic (LQ) problem, which we conjecture stabilizes state dynamics. We support this conjecture by discussing experimental results from a range of optimal control case studies.

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。

↑