Online Linear Quadratic Control

被引：0

作者：

Cohen, Alon ^{[1
,2
]}

Hassidim, Avinatan ^{[1
,3
]}

Koren, Tomer ^{[4
]}

Lazic, Nevena ^{[4
]}

Mansour, Yishay ^{[1
,5
]}

Talwar, Kunal ^{[4
]}

机构：

[1] Google Res, Tel Aviv, Israel

[2] Technion Israel Inst Technol, Haifa, Israel

[3] Bar Ilan Univ, Ramat Gan, Israel

[4] Google Brain, Mountain View, CA 94043 USA

[5] Tel Aviv Univ, Tel Aviv, Israel

来源：

INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 80 | 2018年 / 80卷

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We study the problem of controlling linear time-invariant systems with known noisy dynamics and adversarially chosen quadratic losses. We present the first efficient online learning algorithms in this setting that guarantee O(root 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 to "strongly stable" policies that mix exponentially fast to a steady state.

引用

页数：10

共 50 条

[21] Piecewise linear quadratic optimal control
Rantzer, A
Johansson, M
PROCEEDINGS OF THE 1997 AMERICAN CONTROL CONFERENCE, VOLS 1-6, 1997, : 1749 - 1753
[22] DEAR Linear Dynamic Quadratic Control
Guo, R.
Forrest, J.
Guo, D.
PROCEEDINGS OF THE EIGHTH INTERNATIONAL CONFERENCE ON INFORMATION AND MANAGEMENT SCIENCES, 2009, 8 : 626 - 632
[23] LINEAR-QUADRATIC OPTIMAL CONTROL
COPPEL, WA
PROCEEDINGS OF THE ROYAL SOCIETY OF EDINBURGH SECTION A-MATHEMATICS, 1975, 73 : 271 - 289
[24] A survey of linear quadratic robust control
Bernhard, P
ETFA 2001: 8TH IEEE INTERNATIONAL CONFERENCE ON EMERGING TECHNOLOGIES AND FACTORY AUTOMATION, VOL 1, PROCEEDINGS, 2001, : 75 - 85
[25] Linear-quadratic optimal control with integral quadratic constraints
Lim, AEB
Liu, YQ
Teo, KL
Moore, JB
OPTIMAL CONTROL APPLICATIONS & METHODS, 1999, 20 (02): : 79 - 92
[26] Indefinite stochastic linear quadratic control with integral quadratic constraints
Ma, Hongji
Zhang, Weihai
Hou, Ting
DYNAMICS OF CONTINUOUS DISCRETE AND IMPULSIVE SYSTEMS-SERIES A-MATHEMATICAL ANALYSIS, 2006, 13 : 806 - 811
[27] Linear-quadratic optimal control with integral quadratic constraints
Department of Systems Engineering, Res. Sch. of Info. Sci. and Eng., Australian National University, Canberra, ACT 0200, Australia
不详
Optim Control Appl Methods, 2 (79-92):
[28] Inverse Stochastic Optimal Control for Linear-Quadratic Gaussian and Linear-Quadratic Sensorimotor Control Models
Karg, Philipp
Stoll, Simon
Rothfuss, Simon
Hohmann, Soren
2022 IEEE 61ST CONFERENCE ON DECISION AND CONTROL (CDC), 2022, : 2801 - 2808
[29] Linear quadratic optimal control of networked control system
Wang, Zhi-Wen
Gao, Hong-Hong
2015 27TH CHINESE CONTROL AND DECISION CONFERENCE (CCDC), 2015, : 2177 - 2182
[30] Online Inverse Linear-Quadratic Differential Games Applied to Human Behavior Identification in Shared Control
Inga, Jairo
Creutz, Andreas
Hohmann, Soeren
2021 EUROPEAN CONTROL CONFERENCE (ECC), 2021, : 353 - 360

← 1 2 3 4 5 →