arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.04565eess.SYcs.SYmath.OC
收藏

适应与稳定,然后学习与优化:一种新的自适应LQR方法

Adapt and Stabilize, Then Learn and Optimize: A New Approach to Adaptive LQR

Massachusetts Institute of Technology(麻省理工学院)

Peter A. Fisher, Anuradha M. Annaswamy

AI总结:

本文提出一种新的自适应LQR方法,通过直接模型参考自适应控制与基于周期的方法相结合,克服了现有方法的不足,提供可证明的高概率遗憾界。

摘要:

本文聚焦于离散时间线性二次调节器(自适应LQR)的自适应控制。近期文献在证明非渐近收敛速率方面做出了重要贡献,但现有方法存在一些缺点,阻碍了实际应用。这些缺点包括(i)需要初始稳定控制器,(ii)依赖探索以实现闭环稳定性,以及(iii)计算上耗费大量资源。本文提出了一种新的算法,针对特定类型的离散时间系统克服这些缺点。该算法利用直接模型参考自适应控制(直接MRAC)并结合基于周期的方法,以可证明的高概率遗憾界与现有文献相当的方式解决缺点(i)-(iii)。仿真显示,当满足条件(i)和(ii)时,所提方法的遗憾与现有方法相当,当不满足这两个条件中的任何一个时,其遗憾显著更小。

英文摘要:

This paper focuses on adaptive control of the discrete-time linear quadratic regulator (adaptive LQR). Recent literature has made significant contributions in proving non-asymptotic convergence rates, but existing approaches have a few drawbacks that pose barriers for practical implementation. These drawbacks include (i) a requirement of an initial stabilizing controller, (ii) a reliance on exploration for closed-loop stability, and/or (iii) computationally intensive algorithms. This paper proposes a new algorithm that overcomes these drawbacks for a particular class of discrete-time systems. This algorithm leverages direct model-reference adaptive control (direct MRAC) and combines it with an epoch-based approach in order to address the drawbacks (i)-(iii) with a provable high-probability regret bound comparable to existing literature. Simulations demonstrate that the proposed approach yields regrets that are comparable to those from existing methods when the conditions (i) and (ii) are met, and yields regrets that are significantly smaller when either of these two conditions is not met.

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。

↑