BriefGPT.xyz
Nov, 2020
具有低秩转换的情节线性二次调节器
Episodic Linear Quadratic Regulators with Low-rank Transitions
HTML
PDF
Tianyu Wang, Lin F. Yang
TL;DR
本篇论文提出一种基于系统内在低秩结构进行高效学习的算法，使样本复杂度只依赖于秩而非环境维度，同时获得了关于K的次线性复杂度，在LQR问题的应用中取得了较好效果。
Abstract
linear quadratic regulators
(LQR) achieve enormous successful real-world applications. Very recently, people have been focusing on
efficient learning algorithms
for LQRs when their dynamics are unknown. Existing
→