BriefGPT.xyz
Jan, 2023
精细样本复杂度下的Kalman滤波器学习
Learning the Kalman Filter with Fine-Grained Sample Complexity
HTML
PDF
Xiangyuan Zhang, Bin Hu, Tamer Başar
TL;DR
提出了一种新的RHPG-KF框架，可应用于任何线性动态系统，并且不需要先验知识或系统开环稳定，能够实现稳定滤波器的学习，同时具有省时，高效的特性。
Abstract
We develop the first end-to-end
sample complexity
of
model-free policy gradient
(PG) methods in discrete-time infinite-horizon
kalman filtering
→