arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.05042cs.LGcs.SYeess.SY
收藏

动态输出反馈的优化景观:线性二次调节器的案例研究

On the Optimization Landscape of Dynamic Output Feedback: A Case Study for Linear Quadratic Regulator

National University of Singapore(新加坡国立大学);University of Science and Technology Beijing(北京科技大学);Tsinghua University(清华大学);University of California San Diego(加利福尼亚大学圣迭戈分校)

Jingliang Duan, Wenhan Cao, Yang Zheng, Lin Zhao

AI总结:

本文研究线性二次调节中动态输出反馈的优化景观,证明可观测dLQR驻点唯一且可表示为带最优相似变换的观测器型控制器,为部分观测决策问题的高效算法设计提供理论依据。

摘要:

强化学习中策略梯度算法的收敛性取决于底层最优控制问题的优化景观。对这些算法的理论认识通常可以通过分析线性二次控制的优化景观来获得。然而,现有文献大多只考虑静态全状态或输出反馈策略(控制器)的优化景观。我们研究了更具挑战性的线性二次调节(简称dLQR)的动态输出反馈策略情形,该情形在实践中普遍存在,但其优化景观相当复杂。我们首先展示了dLQR代价如何随动态控制器的坐标变换而变化,然后针对给定的可观测稳定控制器推导出最优变换。我们结果的核心在于:当dLQR可观测时,其驻点是唯一的,其形式简洁地表现为具有最优相似变换的基于观测器的控制器。这些结果有助于为具有部分观测信息的一般决策问题设计高效算法。

英文摘要:

The convergence of policy gradient algorithms in reinforcement learning hinges on the optimization landscape of the underlying optimal control problem. Theoretical insights into these algorithms can often be acquired from analyzing those of linear quadratic control. However, most of the existing literature only considers the optimization landscape for static full-state or output feedback policies (controllers). We investigate the more challenging case of dynamic output-feedback policies for linear quadratic regulation (abbreviated as dLQR), which is prevalent in practice but has a rather complicated optimization landscape. We first show how the dLQR cost varies with the coordinate transformation of the dynamic controller and then derive the optimal transformation for a given observable stabilizing controller. At the core of our results is the uniqueness of the stationary point of dLQR when it is observable, which is in a concise form of an observer-based controller with the optimal similarity transformation. These results shed light on designing efficient algorithms for general decision-making problems with partially observed information.

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。

↑