arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2307.07129eess.SYcs.SY
收藏

平均场线性二次系统的风险约束控制

Risk-Constrained Control of Mean-Field Linear Quadratic Systems

Masoud Roudneshin, Saba Sanami, Amir G. Aghdam

AI总结:

针对平均场设定下的无限时域风险约束 LQR,本文通过约束所有参与者状态代价的累积单阶段方差,得到带风险控制附加项的仿射最优控制器,并提出与参与者数量无关的解决方案。

摘要:

风险中性 LQR 控制器对于随机线性动力系统是最优的。然而,在存在低概率但在统计上显著(有风险)的事件时,经典最优控制器表现低效。本研究聚焦于平均场设定下的无限时域风险约束线性二次调节器。我们通过约束所有参与者状态代价的累积单阶段方差来处理风险约束。研究表明,最优控制器关于每个参与者的状态是仿射的,并带有一个控制风险约束的附加项。此外,我们提出了一种独立于参与者数量的解决方案。最后,给出仿真以验证理论发现。

英文摘要:

The risk-neutral LQR controller is optimal for stochastic linear dynamical systems. However, the classical optimal controller performs inefficiently in the presence of low-probability yet statistically significant (risky) events. The present research focuses on infinite-horizon risk-constrained linear quadratic regulators in a mean-field setting. We address the risk constraint by bounding the cumulative one-stage variance of the state penalty of all players. It is shown that the optimal controller is affine in the state of each player with an additive term that controls the risk constraint. In addition, we propose a solution independent of the number of players. Finally, simulations are presented to verify the theoretical findings.

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。

↑