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

[1] Optimal Routing for Autonomous Taxis using Distributed Reinforcement Learning
Rahili, Salar
Riviere, Benjamin
Oliver, Suzanne
Chung, Soon-Jo
[J]. 2018 18TH IEEE INTERNATIONAL CONFERENCE ON DATA MINING WORKSHOPS (ICDMW), 2018, : 556 - 563
[2] Autonomous Building Control Using Offline Reinforcement Learning
Schepers, Jorren
Eyckerman, Reinout
Elmaz, Furkan
Casteels, Wim
Latre, Steven
Hellinckx, Peter
[J]. ADVANCES ON P2P, PARALLEL, GRID, CLOUD AND INTERNET COMPUTING, 3PGCIC-2021, 2022, 343 : 246 - 255
[3] Path Planning and Energy Optimization in Optimal Control of Autonomous Wheel Loaders Using Reinforcement Learning
Sardarmehni, Tohid
Song, Xingyong
[J]. IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2023, 72 (08) : 9821 - 9834
[4] Reaching the limit in autonomous racing: Optimal control versus reinforcement learning
Song, Yunlong
Romero, Angel
Muller, Matthias
Koltun, Vladlen
Scaramuzza, Davide
[J]. SCIENCE ROBOTICS, 2023, 8 (82)
[5] Docking Control of an Autonomous Underwater Vehicle Using Reinforcement Learning
Anderlini, Enrico
Parker, Gordon G.
Thomas, Giles
[J]. APPLIED SCIENCES-BASEL, 2019, 9 (17):
[6] Steering control in autonomous vehicles using deep reinforcement learning
Xue Chong
Zhang Xinyu
Jia Peng
[J]. The Journal of China Universities of Posts and Telecommunications, 2018, 25 (06) : 58 - 64
[7] Autonomous Navigation and Control of a Quadrotor Using Deep Reinforcement Learning
Mokhtar, Mohamed
El-Badawy, Ayman
[J]. 2023 INTERNATIONAL CONFERENCE ON UNMANNED AIRCRAFT SYSTEMS, ICUAS, 2023, : 1045 - 1052
[8] Autonomous Bus Fleet Control Using Multiagent Reinforcement Learning
Wang, Sung-Jung
Chang, S. K. Jason
[J]. JOURNAL OF ADVANCED TRANSPORTATION, 2021, 2021
[9] Towards autonomous neuroprosthetic control using Hebbian reinforcement learning
Mahmoudi, Babak
Pohlmeyer, Eric A.
Prins, Noeline W.
Geng, Shijia
Sanchez, Justin C.
[J]. JOURNAL OF NEURAL ENGINEERING, 2013, 10 (06)
[10] Wireless Control of Autonomous Guided Vehicle Using Reinforcement Learning
Ana, Pedro M. de Sant
Marchenko, Nikolaj
Popovski, Petar
Soret, Beatriz
[J]. 2020 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM), 2020,

← 1 2 3 4 5 →