Cooperative and adaptive optimal output regulation of discrete-time multi-agent systems using reinforcement learning

Weinan Gao, Yiyang Liu, Adedapo Odekunle, Zhong-Ping Jiang, Yunjun Yu, Pingli Lu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper proposes an original data-driven intelligent control solution to the cooperative output regulation problem of discrete-time multi-agent systems. Based on the combination of internal model principle and reinforcement learning, a distributed suboptimal controller is learned realtime via online input-state data collected from system trajectories. Rigorous theoretical analysis guarantees the convergence of the proposed algorithm and the asymptotic stability of the closed-loop system. Numerical results validate the effectiveness of the proposed control methodology.

Original languageEnglish (US)
Title of host publication2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages348-353
Number of pages6
ISBN (Electronic)9781538668689
DOIs
StatePublished - Jan 22 2019
Event2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018 - Kandima, Maldives
Duration: Aug 1 2018Aug 5 2018

Publication series

Name2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018

Conference

Conference2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018
CountryMaldives
CityKandima
Period8/1/188/5/18

Fingerprint

Output Regulation
Intelligent Control
Intelligent control
Reinforcement learning
Discrete-time Systems
Reinforcement Learning
Asymptotic stability
Multi agent systems
Data-driven
Closed loop systems
Asymptotic Stability
Closed-loop System
Multi-agent Systems
Theoretical Analysis
Trajectories
Trajectory
Internal
Real-time
Controller
Numerical Results

ASJC Scopus subject areas

  • Artificial Intelligence
  • Control and Optimization

Cite this

Gao, W., Liu, Y., Odekunle, A., Jiang, Z-P., Yu, Y., & Lu, P. (2019). Cooperative and adaptive optimal output regulation of discrete-time multi-agent systems using reinforcement learning. In 2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018 (pp. 348-353). [8621852] (2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/RCAR.2018.8621852

Cooperative and adaptive optimal output regulation of discrete-time multi-agent systems using reinforcement learning. / Gao, Weinan; Liu, Yiyang; Odekunle, Adedapo; Jiang, Zhong-Ping; Yu, Yunjun; Lu, Pingli.

2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018. Institute of Electrical and Electronics Engineers Inc., 2019. p. 348-353 8621852 (2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Gao, W, Liu, Y, Odekunle, A, Jiang, Z-P, Yu, Y & Lu, P 2019, Cooperative and adaptive optimal output regulation of discrete-time multi-agent systems using reinforcement learning. in 2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018., 8621852, 2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018, Institute of Electrical and Electronics Engineers Inc., pp. 348-353, 2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018, Kandima, Maldives, 8/1/18. https://doi.org/10.1109/RCAR.2018.8621852
Gao W, Liu Y, Odekunle A, Jiang Z-P, Yu Y, Lu P. Cooperative and adaptive optimal output regulation of discrete-time multi-agent systems using reinforcement learning. In 2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018. Institute of Electrical and Electronics Engineers Inc. 2019. p. 348-353. 8621852. (2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018). https://doi.org/10.1109/RCAR.2018.8621852
Gao, Weinan ; Liu, Yiyang ; Odekunle, Adedapo ; Jiang, Zhong-Ping ; Yu, Yunjun ; Lu, Pingli. / Cooperative and adaptive optimal output regulation of discrete-time multi-agent systems using reinforcement learning. 2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 348-353 (2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018).
@inproceedings{b7b6aa74564c4860ab7f074e8d1ead65,
title = "Cooperative and adaptive optimal output regulation of discrete-time multi-agent systems using reinforcement learning",
abstract = "This paper proposes an original data-driven intelligent control solution to the cooperative output regulation problem of discrete-time multi-agent systems. Based on the combination of internal model principle and reinforcement learning, a distributed suboptimal controller is learned realtime via online input-state data collected from system trajectories. Rigorous theoretical analysis guarantees the convergence of the proposed algorithm and the asymptotic stability of the closed-loop system. Numerical results validate the effectiveness of the proposed control methodology.",
author = "Weinan Gao and Yiyang Liu and Adedapo Odekunle and Zhong-Ping Jiang and Yunjun Yu and Pingli Lu",
year = "2019",
month = "1",
day = "22",
doi = "10.1109/RCAR.2018.8621852",
language = "English (US)",
series = "2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "348--353",
booktitle = "2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018",

}

TY - GEN

T1 - Cooperative and adaptive optimal output regulation of discrete-time multi-agent systems using reinforcement learning

AU - Gao, Weinan

AU - Liu, Yiyang

AU - Odekunle, Adedapo

AU - Jiang, Zhong-Ping

AU - Yu, Yunjun

AU - Lu, Pingli

PY - 2019/1/22

Y1 - 2019/1/22

N2 - This paper proposes an original data-driven intelligent control solution to the cooperative output regulation problem of discrete-time multi-agent systems. Based on the combination of internal model principle and reinforcement learning, a distributed suboptimal controller is learned realtime via online input-state data collected from system trajectories. Rigorous theoretical analysis guarantees the convergence of the proposed algorithm and the asymptotic stability of the closed-loop system. Numerical results validate the effectiveness of the proposed control methodology.

AB - This paper proposes an original data-driven intelligent control solution to the cooperative output regulation problem of discrete-time multi-agent systems. Based on the combination of internal model principle and reinforcement learning, a distributed suboptimal controller is learned realtime via online input-state data collected from system trajectories. Rigorous theoretical analysis guarantees the convergence of the proposed algorithm and the asymptotic stability of the closed-loop system. Numerical results validate the effectiveness of the proposed control methodology.

UR - http://www.scopus.com/inward/record.url?scp=85062499600&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062499600&partnerID=8YFLogxK

U2 - 10.1109/RCAR.2018.8621852

DO - 10.1109/RCAR.2018.8621852

M3 - Conference contribution

T3 - 2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018

SP - 348

EP - 353

BT - 2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -