BriefGPT.xyz
Jun, 2020
在线非线性控制的信息论遗憾界
Information Theoretic Regret Bounds for Online Nonlinear Control
HTML
PDF
Sham Kakade, Akshay Krishnamurthy, Kendall Lowrey, Motoya Ohnishi, Wen Sun
TL;DR
该研究针对未知的非线性动态系统问题,提出了一种基于再生核希尔伯特空间的顺序控制算法,并通过信息理论量来获得近乎最优的遗憾上界,实验结果表明其在多个非线性控制任务中均获得了较好的表现。
Abstract
This work studies the problem of
sequential control
in an unknown, nonlinear dynamical system, where we model the underlying system dynamics as an unknown function in a known
reproducing kernel hilbert space
. Thi
→