Logarithmic Regret for Online Control
| 
82 | 
41 | 
0
Abstract
We study optimal regret bounds for control in linear dynamical systems under adversarially changing strongly convex cost functions, given the knowledge of transition dynamics. This includes several well studied and fundamental frameworks such as the Kalman filter and the linear quadratic regulator. State of the art methods achieve regret which scales as 
where T is the time horizon. We show that the optimal regret in this setting can be significantly smaller, scaling as 
This regret bound is achieved by two different efficient iterative methods, online gradient descent and online natural gradient.
还没有评论，说两句吧！
热门资源
The Variational S...
Unlike traditional images which do not offer in...
Learning to Predi...
Much of model-based reinforcement learning invo...
Stratified Strate...
In this paper we introduce Stratified Strategy ...
A Mathematical Mo...
Direct democracy, where each voter casts one vo...
Rating-Boosted La...
The performance of a recommendation system reli...
智能在线
400-630-6780
聆听.建议反馈
E-mail: support@tusaishared.com
资源分类
