资源分类
》 资源 》论文》Online Linear Quadratic Control

Online Linear Quadratic Control

2020-03-16 | |  63 |   40 |   0

Abstract

We study the problem of controlling linear timeinvariant systems with known noisy dynamics and adversarially chosen quadratic losses. We present the first efficient online learning ? algorithms in setting that guarantee O( T) regret under mild assumptions, where T is the time horizon. Our algorithms rely on a novel SDP relaxation for the steady-state distribution of the system. Crucially and in contrast to previously proposed relaxations the feasible solutions of our SDP all correspond t “strongly stable” policies that mix exponentially fast to a steady state.

上一篇：Randomized Block Cubic Newton Method

下一篇：Improved Training of Generative Adversarial Networks using Representative Features

用户评价
全部评价

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 ...

  • Learning to learn...

    The move from hand-designed features to learned...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...