Data-Driven Q-Learning Control for Nonlinear Systems Involving Parallel Multi-Step Deduction - Details

Author：

Wang, J. (Wang, J..) | Wang, D. (Wang, D..) | Zhao, M. (Zhao, M..) | Qiao, J. (Qiao, J..)

Indexed by：

EI Scopus

Abstract：

When　facing　large　amounts　of　data,　it　is　a　challenging　task　to　optimize　policies　by　using　all　data　at　once.　In　this　paper,　a　data-driven　Q-learning　scheme　with　parallel　multi-step　deduction　is　developed　to　improve　learning　efficiency　using　small　batch　data　for　discrete-time　nonlinear　control.　Specifically,　a　data-driven　model　is　established　by　making　use　of　all　data　in　advance.　Then,　the　proposed　algorithm　can　parallel　deduce　the　small　batch　data　to　effectively　accelerate　the　learning　process.　Furthermore,　we　can　adjust　the　step　size　of　multi-step　deduction　to　balance　the　utilization　between　data　and　model.　The　near-optimal　policy　can　be　obtained　ultimately　by　using　hybrid　data　from　the　real　system　and　data-driven　model.　Finally,　a　torsional　pendulum　plant　is　given　to　demonstrate　the　effectiveness　of　the　proposed　method.　　©　2024　IEEE.

Keyword：

reinforcement learning Q-learning Adaptive critic data-driven control parallel deduction

Author Community：

[ 1 ] [Wang J.]Faculty of Information Technology, Beijing University of Technology, Beijing, 100124, China
[ 2 ] [Wang J.]Beijing University of Technology, Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing, 100124, China
[ 3 ] [Wang J.]Beijing Institute of Artificial Intelligence, Beijing University of Technology, Beijing, 100124, China
[ 4 ] [Wang J.]Beijing University of Technology, Beijing Laboratory of Smart Environmental Protection, Beijing, 100124, China
[ 5 ] [Wang D.]Faculty of Information Technology, Beijing University of Technology, Beijing, 100124, China
[ 6 ] [Wang D.]Beijing University of Technology, Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing, 100124, China
[ 7 ] [Wang D.]Beijing Institute of Artificial Intelligence, Beijing University of Technology, Beijing, 100124, China
[ 8 ] [Wang D.]Beijing University of Technology, Beijing Laboratory of Smart Environmental Protection, Beijing, 100124, China
[ 9 ] [Zhao M.]Faculty of Information Technology, Beijing University of Technology, Beijing, 100124, China
[ 10 ] [Zhao M.]Beijing University of Technology, Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing, 100124, China
[ 11 ] [Zhao M.]Beijing Institute of Artificial Intelligence, Beijing University of Technology, Beijing, 100124, China
[ 12 ] [Zhao M.]Beijing University of Technology, Beijing Laboratory of Smart Environmental Protection, Beijing, 100124, China
[ 13 ] [Qiao J.]Faculty of Information Technology, Beijing University of Technology, Beijing, 100124, China
[ 14 ] [Qiao J.]Beijing University of Technology, Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing, 100124, China
[ 15 ] [Qiao J.]Beijing Institute of Artificial Intelligence, Beijing University of Technology, Beijing, 100124, China
[ 16 ] [Qiao J.]Beijing University of Technology, Beijing Laboratory of Smart Environmental Protection, Beijing, 100124, China

Reprint Author's Address：

Email：

Show more details

Related Keywords：

Policy Gradient Adaptive Critic Design With Dynamic Prioritized Experience Replay for Wastewater Treatment Process Control
2022，IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
Novel Discounted Adaptive Critic Control Designs With Accelerated Learning Formulation
2023，IEEE TRANSACTIONS ON CYBERNETICS
Discounted Iterative Adaptive Critic Designs With Novel Stability Analysis for Tracking Control
2022，IEEE-CAA JOURNAL OF AUTOMATICA SINICA
Adaptive Critic Control Design With Knowledge Transfer for Wastewater Treatment Applications
2023，IEEE Transactions on Industrial Informatics

Source ：

Year： 2024

Page： 739-744

Language： English

Cited Count：

WoS CC Cited Count：

SCOPUS Cited Count：

ESI Highly Cited Papers on the List： 0 Unfold All

WanFang Cited Count：

Chinese Cited Count：

30 Days PV： 8

Affiliated Colleges：

Get Fulltext

DOI Library Discovery Baidu Scholar Search SCOPUS

Type
Departments

All Years Choose Year From to