arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.12167eess.SYcs.SY
收藏

具有乘性不确定性的数据驱动随机LQR的样本复杂性

Sample Complexity of Data-Driven Stochastic LQR with Multiplicative Uncertainty

Peter Coppens, Panagiotis Patrinos

摘要:

研究了随机线性二次型调节器应用于带乘性噪声系统时的样本复杂性。我们假设噪声的协方差是未知的,并使用样本协方差对其进行估计,这会导致次优行为。本文的主要贡献是,然后绑定的次优的方法,并证明它减少1/N,其中N表示的样本量。该方法很容易推广到的情况下,平均值是未知的,并在以前的工作中的作者研究的分布鲁棒的情况下。分析主要是基于矩阵函数摄动分析的结果。

英文摘要:

This paper studies the sample complexity of the stochastic Linear Quadratic Regulator when applied to systems with multiplicative noise. We assume that the covariance of the noise is unknown and estimate it using the sample covariance, which results in suboptimal behaviour. The main contribution of this paper is then to bound the suboptimality of the methodology and prove that it decreases with 1/N, where N denotes the amount of samples. The methodology easily generalizes to the case where the mean is unknown and to the distributionally robust case studied in a previous work of the authors. The analysis is mostly based on results from matrix function perturbation analysis.

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。

↑