Optimal and Autonomous Control Using Reinforcement Learning: A Survey

被引：539

作者：

Kiumarsi, Bahare ^{[1
]}

Vamvoudakis, Kyriakos G. ^{[2
]}

Modares, Hamidreza ^{[3
]}

Lewis, Frank L. ^{[1
,4
]}

机构：

[1] Univ Texas Arlington, UTA Res Inst, Arlington, TX 76118 USA

[2] Virginia Tech, Kevin T Crofton Dept Aerosp & Ocean Engn, Blacksburg, VA 24061 USA

[3] Missouri Univ Sci & Technol, Dept Elect & Comp Engn, Rolla, MO 65401 USA

[4] Northeastern Univ, State Key Lab Synthet Automat Proc Ind, Shenyang 110004, Liaoning, Peoples R China

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS | 2018年 / 29卷 / 06期

基金：

美国国家科学基金会;

关键词：

Autonomy; data-based optimization; reinforcement learning (RL); DISCRETE-TIME-SYSTEMS; H-INFINITY CONTROL; OPTIMAL TRACKING CONTROL; ADAPTIVE OPTIMAL-CONTROL; APPROXIMATE OPTIMAL-CONTROL; ZERO-SUM GAMES; LINEAR-SYSTEMS; NONLINEAR-SYSTEMS; FEEDBACK; ALGORITHM;

D O I：

10.1109/TNNLS.2017.2773458

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper reviews the current state of the art on reinforcement learning (RL)-based feedback control solutions to optimal regulation and tracking of single and multiagent systems. Existing RL solutions to both optimal H-2 and H-infinity control problems, as well as graphical games, will be reviewed. RL methods learn the solution to optimal control and game problems online and using measured data along the system trajectories. We discuss Q-learning and the integral RL algorithm as core algorithms for discrete-time (DT) and continuous-time (CT) systems, respectively. Moreover, we discuss a new direction of off-policy RL for both CT and DT systems. Finally, we review several applications.

引用

页码：2042 / 2062

页数：21

共 50 条

[21] Autonomous Surface Vehicle Control Method Using Deep Reinforcement Learning
Zhang, Shang
Yang, Rui
Chen, Zhen
Li, Ming
[J]. 2020 CHINESE AUTOMATION CONGRESS (CAC 2020), 2020, : 1664 - 1668
[22] Autonomous Decentralized Control of Distribution Network Voltage using Reinforcement Learning
Takayama, Satoshi
Ishigame, Atsushi
[J]. IFAC PAPERSONLINE, 2018, 51 (28): : 209 - 214
[23] Autonomous Grading Work Using Deep Reinforcement Learning Based Control
Nakatani, Masayuki
Sun, Zeyuan
Uchimura, Yutaka
[J]. IECON 2018 - 44TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY, 2018, : 5068 - 5073
[24] Networked and Deep Reinforcement Learning-Based Control for Autonomous Marine Vehicles: A Survey
Wang, Yu-Long
Wang, Cheng-Cheng
Han, Qing-Long
Wang, Xiaofan
[J]. IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2024, : 1 - 14
[25] Constrained adaptive optimal control using a reinforcement learning agent
Lin, Wei-Song
Zheng, Chen-Hong
[J]. AUTOMATICA, 2012, 48 (10) : 2614 - 2619
[26] Optimal Balancing Control of Bipedal Robots Using Reinforcement Learning
Peng, Fang
Ding, Lijia
Li, Zhijun
Yang, Chenguang
Su, Chun-Yi
[J]. PROCEEDINGS OF THE 2016 12TH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION (WCICA), 2016, : 2186 - 2191
[27] Exploring optimal control of epidemic spread using reinforcement learning
Abu Quwsar Ohi
M. F. Mridha
Muhammad Mostafa Monowar
Md. Abdul Hamid
[J]. Scientific Reports, 10
[28] Exploring optimal control of epidemic spread using reinforcement learning
Ohi, Abu Quwsar
Mridha, M. F.
Monowar, Muhammad Mostafa
Hamid, Md. Abdul
[J]. SCIENTIFIC REPORTS, 2020, 10 (01)
[29] Online Reinforcement Learning for Autonomous Sensor Control
Ravier, Robert
Garagic, Denis
Peskoe, Jacob
Galoppo, Travis
Tigue, James
Rhodes, Bradley J.
Zulch, Peter
[J]. 2023 IEEE AEROSPACE CONFERENCE, 2023,
[30] Hybrid reinforcement learning for autonomous UAV control
Yoo, Jae Hyun
[J]. Journal of Institute of Control, Robotics and Systems, 2019, 25 (06) : 546 - 550

← 1 2 3 4 5 →