Model-free algorithm for consensus of discrete-time multi-agent systems using reinforcement learning method

In this work, we investigate consensus issues of discrete-time (DT) multi-agent systems (MASs) with completely unknown dynamic by using reinforcement learning (RL) technique. Different from policy iteration (PI) based algorithms that require admissible initial control policies, this work proposes a...

Full description

Saved in:
Bibliographic Details
Published inJournal of the Franklin Institute Vol. 360; no. 14; pp. 10564 - 10581
Main Authors Long, Mingkang, An, Qing, Su, Housheng, Luo, Hui, Zhao, Jin
Format Journal Article
LanguageEnglish
Published Elsevier Inc 01.09.2023
Online AccessGet full text
ISSN0016-0032
1879-2693
DOI10.1016/j.jfranklin.2023.08.010

Cover

Abstract In this work, we investigate consensus issues of discrete-time (DT) multi-agent systems (MASs) with completely unknown dynamic by using reinforcement learning (RL) technique. Different from policy iteration (PI) based algorithms that require admissible initial control policies, this work proposes a value iteration (VI) based model-free algorithm for consensus of DTMASs with optimal performance and no requirement of admissible initial control policy. Firstly, in order to utilize RL method, the consensus problem is modeled as an optimal control problem of tracking error system for each agent. Then, we introduce a VI algorithm for consensus of DTMASs and give a novel convergence analysis for this algorithm, which does not require admissible initial control input. To implement the proposed VI algorithm to achieve consensus of DTMASs without information of dynamics, we construct actor-critic networks to online estimate the value functions and optimal control inputs in real time. At last, we give some simulation results to show the validity of the proposed algorithm.
AbstractList In this work, we investigate consensus issues of discrete-time (DT) multi-agent systems (MASs) with completely unknown dynamic by using reinforcement learning (RL) technique. Different from policy iteration (PI) based algorithms that require admissible initial control policies, this work proposes a value iteration (VI) based model-free algorithm for consensus of DTMASs with optimal performance and no requirement of admissible initial control policy. Firstly, in order to utilize RL method, the consensus problem is modeled as an optimal control problem of tracking error system for each agent. Then, we introduce a VI algorithm for consensus of DTMASs and give a novel convergence analysis for this algorithm, which does not require admissible initial control input. To implement the proposed VI algorithm to achieve consensus of DTMASs without information of dynamics, we construct actor-critic networks to online estimate the value functions and optimal control inputs in real time. At last, we give some simulation results to show the validity of the proposed algorithm.
Author Su, Housheng
An, Qing
Luo, Hui
Zhao, Jin
Long, Mingkang
Author_xml – sequence: 1
  givenname: Mingkang
  surname: Long
  fullname: Long, Mingkang
  organization: School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China, Wuhan 430074, China
– sequence: 2
  givenname: Qing
  surname: An
  fullname: An, Qing
  organization: Artificial Intelligence School, Wuchang University of Technology, Wuhan 430223, China
– sequence: 3
  givenname: Housheng
  orcidid: 0000-0002-7321-2923
  surname: Su
  fullname: Su, Housheng
  email: houshengsu@gmail.com, shs@hust.edu.cn
  organization: School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China, Wuhan 430074, China
– sequence: 4
  givenname: Hui
  surname: Luo
  fullname: Luo, Hui
  organization: School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China, Wuhan 430074, China
– sequence: 5
  givenname: Jin
  surname: Zhao
  fullname: Zhao, Jin
  organization: School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China, Wuhan 430074, China
BookMark eNqNkMtKAzEUhoMoWKvPYF5gxpNM5tKFi1K8QcWNrkOanLRpZxJJUsG3d0rFhRtdHc7l--F8F-TUB4-EXDMoGbDmZltubVR-1ztfcuBVCV0JDE7IhHXtrODNrDolExhPC4CKn5OLlLZj2zKACdk9B4N9YSMiVf06RJc3A7UhUh18Qp_2iQZLjUs6YsYiuwHpsO-zK9QafabpM2UcEt0n59c0ovMjrHE47HpU0R_GA-ZNMJfkzKo-4dV3nZK3-7vXxWOxfHl4WsyXha5YnYtGcysaMHW3ErCqdAPIBG9sh8pYZphSpq5WeiaqmgkGRoiW8ZXgTLSC13VTTUl7zNUxpBTRyvfoBhU_JQN5cCa38seZPDiT0MnR2Uje_iK1yyq74HNUrv8HPz_yOL734TDKpB16jcZF1Fma4P7M-AJzSZKP
CitedBy_id crossref_primary_10_1016_j_ins_2024_121196
crossref_primary_10_1016_j_neucom_2025_129846
crossref_primary_10_1109_TSIPN_2024_3419437
Cites_doi 10.1109/TCYB.2015.2492242
10.1016/j.jfranklin.2021.02.022
10.1109/TAC.2007.904277
10.1109/TAC.2022.3184630
10.1016/j.jfranklin.2020.07.008
10.1016/j.automatica.2014.10.047
10.1109/TCYB.2019.2948209
10.1007/s11768-015-3203-x
10.1016/j.automatica.2011.03.005
10.1049/iet-cta.2018.6266
10.1109/TCYB.2020.2987385
10.1109/TAC.2022.3184652
10.1109/TIE.2016.2542134
10.1109/TNN.2009.2027233
10.1109/TMECH.2009.2014057
10.1016/j.jfranklin.2018.06.006
10.1063/1.5120106
10.1016/j.jfranklin.2020.12.033
10.1016/j.automatica.2022.110645
ContentType Journal Article
Copyright 2023 The Franklin Institute
Copyright_xml – notice: 2023 The Franklin Institute
DBID AAYXX
CITATION
DOI 10.1016/j.jfranklin.2023.08.010
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1879-2693
EndPage 10581
ExternalDocumentID 10_1016_j_jfranklin_2023_08_010
S001600322300501X
GroupedDBID --K
--M
-DZ
-~X
.~1
0R~
1B1
1RT
1~.
1~5
29L
4.4
41~
457
4G.
5GY
5VS
6TJ
7-5
71M
8P~
9JN
9JO
AAAKF
AAAKG
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AARIN
AAXUO
AAYFN
ABAOU
ABBOA
ABEFU
ABFRF
ABJNI
ABMAC
ABTAH
ABUCO
ABXDB
ABYKQ
ACAZW
ACCUC
ACDAQ
ACGFO
ACGFS
ACIWK
ACNCT
ACNNM
ACRLP
ACZNC
ADEZE
ADGUI
ADJOM
ADMUD
ADTZH
AEBSH
AECPX
AEFWE
AEKER
AETEA
AFDAS
AFFNX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHJVU
AHZHX
AIALX
AIEXJ
AIGVJ
AIKHN
AITUG
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
APLSM
ARUGR
AXJTR
BJAXD
BKOJK
BLXMC
CS3
D1Z
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
F5P
FA8
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-2
G-Q
G8K
GBLVA
GBOLZ
HAMUX
HMJ
HVGLF
HZ~
H~9
IHE
J1W
JJJVA
KOM
LY7
M26
M41
MHUIS
MO0
MVM
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
R2-
RIG
ROL
RPZ
SCC
SDF
SDG
SES
SET
SEW
SME
SPC
SPCBC
SSB
SSD
SST
SSV
SSW
SSZ
T5K
TN5
UHS
VOH
WH7
WUQ
XOL
XPP
ZCG
ZMT
ZY4
~02
~G-
AATTM
AAXKI
AAYWO
AAYXX
ABDPE
ABWVN
ACLOT
ACRPL
ADNMO
ADXHL
AEIPS
AFJKZ
AGQPQ
AHPAA
AIIUN
ANKPU
APXCP
CITATION
EFKBS
~HD
ID FETCH-LOGICAL-c315t-6c2f460d58b40b3c60e1426f8eadf1d1aad53bc94351410d44712b42147425563
IEDL.DBID .~1
ISSN 0016-0032
IngestDate Wed Oct 01 05:31:44 EDT 2025
Thu Apr 24 22:59:31 EDT 2025
Fri Feb 23 02:35:31 EST 2024
IsPeerReviewed true
IsScholarly true
Issue 14
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c315t-6c2f460d58b40b3c60e1426f8eadf1d1aad53bc94351410d44712b42147425563
ORCID 0000-0002-7321-2923
PageCount 18
ParticipantIDs crossref_primary_10_1016_j_jfranklin_2023_08_010
crossref_citationtrail_10_1016_j_jfranklin_2023_08_010
elsevier_sciencedirect_doi_10_1016_j_jfranklin_2023_08_010
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate September 2023
2023-09-00
PublicationDateYYYYMMDD 2023-09-01
PublicationDate_xml – month: 09
  year: 2023
  text: September 2023
PublicationDecade 2020
PublicationTitle Journal of the Franklin Institute
PublicationYear 2023
Publisher Elsevier Inc
Publisher_xml – name: Elsevier Inc
References Liu, Fan, Jia (bib0002) 2020; 357
Rizvi, Lin (bib0019) 2019; 13
Bertsekas, Tsitsiklis (bib0015) 1996
Ren, Beard, Atkins (bib0011) 2005; Vol .3
Abouheaf, Lewis, Vamvoudakis, Haesaert, Babuska (bib0016) 2014; 50
Li, Duan (bib0022) 2014
Su, Wang, Gao (bib0005) 2023; 68
Tabuada (bib0009) 2007; 52
Long, Su, Liu (bib0003) 2018; 355
Zhang, Wu, Cao (bib0008) 2021; 358
Long, Su, Zeng (bib0021) 2022; 52
Abouheaf, Lewis, Mahmoud (bib0017) 2015; 13
Yao, Dou, Zhao, Zhang (bib0001) 2021; 358
Long, Su, Wang, Jiang, Wang (bib0020) 2019; 29
Su, Wang, Zeng (bib0010) 2020; 50
Vamvoudakis, Lewis (bib0012) 2011; 47
Li, An, Su (bib0006) 2023; 444
Wei, Liu, Lin (bib0014) 2016; 46
Khoo, Xie, Man (bib0023) 2009; 14
Su, Miao (bib0004) 2023; 68
Su, Xu (bib0007) 2022; 146
Zhang, Luo, Liu (bib0024) 2009; 20
Zhang, Jiang, Luo, Xiao (bib0018) 2017; 64
Sutton, Barto (bib0013) 1998
Khoo (10.1016/j.jfranklin.2023.08.010_bib0023) 2009; 14
Abouheaf (10.1016/j.jfranklin.2023.08.010_bib0017) 2015; 13
Zhang (10.1016/j.jfranklin.2023.08.010_bib0024) 2009; 20
Tabuada (10.1016/j.jfranklin.2023.08.010_bib0009) 2007; 52
Zhang (10.1016/j.jfranklin.2023.08.010_bib0008) 2021; 358
Bertsekas (10.1016/j.jfranklin.2023.08.010_bib0015) 1996
Long (10.1016/j.jfranklin.2023.08.010_bib0021) 2022; 52
Sutton (10.1016/j.jfranklin.2023.08.010_bib0013) 1998
Abouheaf (10.1016/j.jfranklin.2023.08.010_bib0016) 2014; 50
Yao (10.1016/j.jfranklin.2023.08.010_bib0001) 2021; 358
Liu (10.1016/j.jfranklin.2023.08.010_bib0002) 2020; 357
Su (10.1016/j.jfranklin.2023.08.010_bib0004) 2023; 68
Li (10.1016/j.jfranklin.2023.08.010_bib0006) 2023; 444
Li (10.1016/j.jfranklin.2023.08.010_bib0022) 2014
Su (10.1016/j.jfranklin.2023.08.010_bib0007) 2022; 146
Vamvoudakis (10.1016/j.jfranklin.2023.08.010_bib0012) 2011; 47
Rizvi (10.1016/j.jfranklin.2023.08.010_bib0019) 2019; 13
Su (10.1016/j.jfranklin.2023.08.010_bib0005) 2023; 68
Su (10.1016/j.jfranklin.2023.08.010_bib0010) 2020; 50
Zhang (10.1016/j.jfranklin.2023.08.010_bib0018) 2017; 64
Long (10.1016/j.jfranklin.2023.08.010_bib0003) 2018; 355
Wei (10.1016/j.jfranklin.2023.08.010_bib0014) 2016; 46
Ren (10.1016/j.jfranklin.2023.08.010_bib0011) 2005; Vol .3
Long (10.1016/j.jfranklin.2023.08.010_bib0020) 2019; 29
References_xml – volume: 14
  start-page: 219
  year: 2009
  end-page: 228
  ident: bib0023
  article-title: Robust finite-time consensus tracking algorithm for multirobot systems
  publication-title: IEEE/ASME Trans. Mechatron.
– volume: 357
  start-page: 9268
  year: 2020
  end-page: 9287
  ident: bib0002
  article-title: Iterative learning formation control for continuous-time multi-agent systems with randomly varying trial lengths
  publication-title: J. Franklin Inst.
– volume: 358
  start-page: 3512
  year: 2021
  end-page: 3529
  ident: bib0001
  article-title: Finite-time consensus control for a class of multi-agent systems with dead-zone input
  publication-title: J. Franklin Inst.
– volume: 13
  start-page: 55
  year: 2015
  end-page: 69
  ident: bib0017
  article-title: Discrete-time dynamic graphical games: model-free reinforcement learning solution
  publication-title: Control Theory Technol.
– volume: 358
  start-page: 2086
  year: 2021
  end-page: 2114
  ident: bib0008
  article-title: Global Mittag-Leffler consensus for fractional singularly perturbed multi-agent systems with discontinuous inherent dynamics via event-triggered control strategy
  publication-title: J. Franklin Inst.
– year: 2014
  ident: bib0022
  article-title: Cooperative Control of Multi-Agent Systems: A Consensus Region Approach
– volume: 29
  start-page: 103127
  year: 2019
  ident: bib0020
  article-title: An iterative q-learning based global consensus of discrete-time saturated multi-agent systems
  publication-title: Chaos
– volume: 355
  start-page: 6045
  year: 2018
  end-page: 6061
  ident: bib0003
  article-title: Group controllability of two-time-scale multi-agent networks
  publication-title: J. Franklin Inst.
– volume: 47
  start-page: 1556
  year: 2011
  end-page: 1569
  ident: bib0012
  article-title: Multi-player non-zero-sum games: online adaptive learning solution of coupled Hamilton-Jacobi equations
  publication-title: Automatica
– volume: 46
  start-page: 840
  year: 2016
  end-page: 853
  ident: bib0014
  article-title: Value iteration adaptive dynamic programming for optimal control of discrete-time nonlinear systems
  publication-title: IEEE Trans. Cybern.
– volume: 52
  start-page: 1680
  year: 2007
  end-page: 1685
  ident: bib0009
  article-title: Event-triggered real-time scheduling of stabilizing control tasks
  publication-title: IEEE Trans. Automat. Contr.
– year: 1998
  ident: bib0013
  article-title: Reinforcement Learning: An Introduction
– volume: 50
  start-page: 3038
  year: 2014
  end-page: 3053
  ident: bib0016
  article-title: Multi-agent discrete-time graphical games and reinforcement learning solutions
  publication-title: Automatica
– volume: 68
  start-page: 2552
  year: 2023
  end-page: 2559
  ident: bib0005
  article-title: Interval coordination of multiagent networks with antagonistic interactions
  publication-title: IEEE Trans. Automat. Contr.
– volume: 146
  start-page: 110645
  year: 2022
  ident: bib0007
  article-title: Deployment of second-order networked mobile agents over a smooth curve
  publication-title: Automatica
– volume: 68
  start-page: 2529
  year: 2023
  end-page: 2535
  ident: bib0004
  article-title: Consensus on directed matrix-weighted networks
  publication-title: IEEE Trans. Automat. Contr.
– volume: Vol .3
  start-page: 1859
  year: 2005
  end-page: 1864
  ident: bib0011
  article-title: A survey of consensus problems in multi-agent coordination
  publication-title: Proceedings of the 2005 American Control Conference
– year: 1996
  ident: bib0015
  article-title: Neuro-Dynamic Programming
– volume: 13
  start-page: 2866
  year: 2019
  end-page: 2876
  ident: bib0019
  article-title: Output feedback reinforcement learning based optimal output synchronisation of heterogeneous discrete-time multi-agent systems
  publication-title: IET Control Theory Appl.
– volume: 52
  start-page: 1661
  year: 2022
  end-page: 1670
  ident: bib0021
  article-title: Output-feedback global consensus of discrete-time multiagent systems subject to input saturation via q-learning method
  publication-title: IEEE Trans. Cybern.
– volume: 444
  start-page: 127801
  year: 2023
  ident: bib0006
  article-title: Proximal nested primal-dual gradient algorithms for distributed constraint-coupled composite optimization
  publication-title: Appl. Math. Comput.
– volume: 50
  start-page: 4648
  year: 2020
  end-page: 4657
  ident: bib0010
  article-title: Consensus of second-order hybrid multiagent systems by event-triggered strategy
  publication-title: IEEE Trans. Cybern.
– volume: 20
  start-page: 1490
  year: 2009
  end-page: 1503
  ident: bib0024
  article-title: Neural-network-based near-optimal control for a class of discrete-time affine nonlinear systems with control constraints
  publication-title: IEEE Trans. Neural Netw.
– volume: 64
  start-page: 4091
  year: 2017
  end-page: 4100
  ident: bib0018
  article-title: Data-driven optimal consensus control for discrete-time multi-agent systems with unknown dynamics using reinforcement learning method
  publication-title: IEEE Trans. Ind. Electron.
– year: 1998
  ident: 10.1016/j.jfranklin.2023.08.010_bib0013
– volume: 46
  start-page: 840
  issue: 3
  year: 2016
  ident: 10.1016/j.jfranklin.2023.08.010_bib0014
  article-title: Value iteration adaptive dynamic programming for optimal control of discrete-time nonlinear systems
  publication-title: IEEE Trans. Cybern.
  doi: 10.1109/TCYB.2015.2492242
– volume: 358
  start-page: 3512
  issue: 7
  year: 2021
  ident: 10.1016/j.jfranklin.2023.08.010_bib0001
  article-title: Finite-time consensus control for a class of multi-agent systems with dead-zone input
  publication-title: J. Franklin Inst.
  doi: 10.1016/j.jfranklin.2021.02.022
– volume: Vol .3
  start-page: 1859
  year: 2005
  ident: 10.1016/j.jfranklin.2023.08.010_bib0011
  article-title: A survey of consensus problems in multi-agent coordination
– volume: 52
  start-page: 1680
  issue: 9
  year: 2007
  ident: 10.1016/j.jfranklin.2023.08.010_bib0009
  article-title: Event-triggered real-time scheduling of stabilizing control tasks
  publication-title: IEEE Trans. Automat. Contr.
  doi: 10.1109/TAC.2007.904277
– volume: 68
  start-page: 2529
  issue: 4
  year: 2023
  ident: 10.1016/j.jfranklin.2023.08.010_bib0004
  article-title: Consensus on directed matrix-weighted networks
  publication-title: IEEE Trans. Automat. Contr.
  doi: 10.1109/TAC.2022.3184630
– volume: 357
  start-page: 9268
  issue: 14
  year: 2020
  ident: 10.1016/j.jfranklin.2023.08.010_bib0002
  article-title: Iterative learning formation control for continuous-time multi-agent systems with randomly varying trial lengths
  publication-title: J. Franklin Inst.
  doi: 10.1016/j.jfranklin.2020.07.008
– volume: 444
  start-page: 127801
  year: 2023
  ident: 10.1016/j.jfranklin.2023.08.010_bib0006
  article-title: Proximal nested primal-dual gradient algorithms for distributed constraint-coupled composite optimization
  publication-title: Appl. Math. Comput.
– volume: 50
  start-page: 3038
  issue: 12
  year: 2014
  ident: 10.1016/j.jfranklin.2023.08.010_bib0016
  article-title: Multi-agent discrete-time graphical games and reinforcement learning solutions
  publication-title: Automatica
  doi: 10.1016/j.automatica.2014.10.047
– volume: 50
  start-page: 4648
  issue: 11
  year: 2020
  ident: 10.1016/j.jfranklin.2023.08.010_bib0010
  article-title: Consensus of second-order hybrid multiagent systems by event-triggered strategy
  publication-title: IEEE Trans. Cybern.
  doi: 10.1109/TCYB.2019.2948209
– volume: 13
  start-page: 55
  issue: 1
  year: 2015
  ident: 10.1016/j.jfranklin.2023.08.010_bib0017
  article-title: Discrete-time dynamic graphical games: model-free reinforcement learning solution
  publication-title: Control Theory Technol.
  doi: 10.1007/s11768-015-3203-x
– year: 2014
  ident: 10.1016/j.jfranklin.2023.08.010_bib0022
– volume: 47
  start-page: 1556
  issue: 8
  year: 2011
  ident: 10.1016/j.jfranklin.2023.08.010_bib0012
  article-title: Multi-player non-zero-sum games: online adaptive learning solution of coupled Hamilton-Jacobi equations
  publication-title: Automatica
  doi: 10.1016/j.automatica.2011.03.005
– volume: 13
  start-page: 2866
  issue: 17
  year: 2019
  ident: 10.1016/j.jfranklin.2023.08.010_bib0019
  article-title: Output feedback reinforcement learning based optimal output synchronisation of heterogeneous discrete-time multi-agent systems
  publication-title: IET Control Theory Appl.
  doi: 10.1049/iet-cta.2018.6266
– volume: 52
  start-page: 1661
  issue: 3
  year: 2022
  ident: 10.1016/j.jfranklin.2023.08.010_bib0021
  article-title: Output-feedback global consensus of discrete-time multiagent systems subject to input saturation via q-learning method
  publication-title: IEEE Trans. Cybern.
  doi: 10.1109/TCYB.2020.2987385
– volume: 68
  start-page: 2552
  issue: 4
  year: 2023
  ident: 10.1016/j.jfranklin.2023.08.010_bib0005
  article-title: Interval coordination of multiagent networks with antagonistic interactions
  publication-title: IEEE Trans. Automat. Contr.
  doi: 10.1109/TAC.2022.3184652
– volume: 64
  start-page: 4091
  issue: 5
  year: 2017
  ident: 10.1016/j.jfranklin.2023.08.010_bib0018
  article-title: Data-driven optimal consensus control for discrete-time multi-agent systems with unknown dynamics using reinforcement learning method
  publication-title: IEEE Trans. Ind. Electron.
  doi: 10.1109/TIE.2016.2542134
– year: 1996
  ident: 10.1016/j.jfranklin.2023.08.010_bib0015
– volume: 20
  start-page: 1490
  issue: 9
  year: 2009
  ident: 10.1016/j.jfranklin.2023.08.010_bib0024
  article-title: Neural-network-based near-optimal control for a class of discrete-time affine nonlinear systems with control constraints
  publication-title: IEEE Trans. Neural Netw.
  doi: 10.1109/TNN.2009.2027233
– volume: 14
  start-page: 219
  issue: 2
  year: 2009
  ident: 10.1016/j.jfranklin.2023.08.010_bib0023
  article-title: Robust finite-time consensus tracking algorithm for multirobot systems
  publication-title: IEEE/ASME Trans. Mechatron.
  doi: 10.1109/TMECH.2009.2014057
– volume: 355
  start-page: 6045
  issue: 13
  year: 2018
  ident: 10.1016/j.jfranklin.2023.08.010_bib0003
  article-title: Group controllability of two-time-scale multi-agent networks
  publication-title: J. Franklin Inst.
  doi: 10.1016/j.jfranklin.2018.06.006
– volume: 29
  start-page: 103127
  issue: 10
  year: 2019
  ident: 10.1016/j.jfranklin.2023.08.010_bib0020
  article-title: An iterative q-learning based global consensus of discrete-time saturated multi-agent systems
  publication-title: Chaos
  doi: 10.1063/1.5120106
– volume: 358
  start-page: 2086
  issue: 3
  year: 2021
  ident: 10.1016/j.jfranklin.2023.08.010_bib0008
  article-title: Global Mittag-Leffler consensus for fractional singularly perturbed multi-agent systems with discontinuous inherent dynamics via event-triggered control strategy
  publication-title: J. Franklin Inst.
  doi: 10.1016/j.jfranklin.2020.12.033
– volume: 146
  start-page: 110645
  year: 2022
  ident: 10.1016/j.jfranklin.2023.08.010_bib0007
  article-title: Deployment of second-order networked mobile agents over a smooth curve
  publication-title: Automatica
  doi: 10.1016/j.automatica.2022.110645
SSID ssj0017100
Score 2.4042578
Snippet In this work, we investigate consensus issues of discrete-time (DT) multi-agent systems (MASs) with completely unknown dynamic by using reinforcement learning...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 10564
Title Model-free algorithm for consensus of discrete-time multi-agent systems using reinforcement learning method
URI https://dx.doi.org/10.1016/j.jfranklin.2023.08.010
Volume 360
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Baden-Württemberg Complete Freedom Collection (Elsevier)
  customDbUrl:
  eissn: 1879-2693
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0017100
  issn: 0016-0032
  databaseCode: GBLVA
  dateStart: 20110101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
– providerCode: PRVESC
  databaseName: Elsevier SD Complete Freedom Collection [SCCMFC]
  customDbUrl:
  eissn: 1879-2693
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0017100
  issn: 0016-0032
  databaseCode: ACRLP
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
– providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection
  customDbUrl:
  eissn: 1879-2693
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0017100
  issn: 0016-0032
  databaseCode: .~1
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
– providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals [SCFCJ]
  customDbUrl:
  eissn: 1879-2693
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0017100
  issn: 0016-0032
  databaseCode: AIKHN
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3Na8IwFA_iLtth7JO5D8lh12hi09ruJjJxG_M0wVtJ0sTpXCtVr_vbl9emojDwsGNLH5TX1_dey-8DoccOGL4bIYgCtVuuI_vOBV2PREKB1bFhorADeh8FwzF_nfiTGupXXBiAVbreX_b0olu7M22XzfZyNgOOL7PT2hYkKK5TNgEGO--Ci0HrZwvzYKBeU3Zj--Vsr97DeM2Nc0ZvgYt4oeUJVNq_JtTO1BmcoVO3LuJeeUfnqKbTC3SyIyJ4ib7AzmxBTK41FotpZr_2P7-x3UWxAqR0utqscGYw0G9zuyETcJPHBY6QCOBV4VLMeYUBAj_FuS60VFXx2xA7U4kpLp2mr9B48PzRHxJnoUCUx_w1CVTH8IAmfig5lZ4KqGZ2JpvQFpBhCRMi8T2pIg6AfkYTm0DWkRzMiziIk3nXqJ5mqb5BmCo_8SJBPdsVeCKTUDJjqAgjyXRgTNhAQZW2WDl9cbC5WMQVkGweb_MdQ75jMMBktIHoNnBZSmwcDnmqnku8Vy2xHQSHgm__E3yHjuGoRJndo_o63-gHu5asZbOouyY66r28DUe_DPDkpQ
linkProvider Elsevier
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LT8JAEN4gHtSD8RnxuQevhd12W1pvhkhQgRMk3Dbb7S6CWEiBq7_dnXZLIDHx4LXtJM10dh7NN9-H0KMLgu9aCEcC2y1TkTlzQdNzIiFB6lhTkcsB9fpBZ8jeRv6oglrlLgzAKm3uL3J6nq3tlYb1ZmMxmcCOLzXV2gQkMK4TOtpD-8x3mzCB1b83OA8K9DVFOjajs3l8B-Q11VYavQ4y4jmZJ-zS_laitspO-wQd234RPxevdIoqKj1DR1ssgufoE_TMZo7OlMJiNp6bcf_jC5tmFEuASqfL9RLPNYb928y0yA7IyeMcSOgIWKzCBZvzEgMGfowzlZOpyvy_IbaqEmNcSE1foGH7ZdDqOFZDwZEe9VdOIF3NApL4YcxI7MmAKGqKsg5NBGmaUCES34tlxADRT0nCTLFyYwbqRQzYybxLVE3nqbpCmEg_8SJBPJMWWBInYUy1JiKMYqoCrcMaCkq3cWkJxkHnYsZLJNmUb_zNwd8cFDApqSGyMVwUHBt_mzyV34XvhAs3leAv4-v_GD-gg86g1-Xd1_77DTqEOwXk7BZVV9la3ZkeZRXf5zH4A2l75jo
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Model-free+algorithm+for+consensus+of+discrete-time+multi-agent+systems+using+reinforcement+learning+method&rft.jtitle=Journal+of+the+Franklin+Institute&rft.au=Long%2C+Mingkang&rft.au=An%2C+Qing&rft.au=Su%2C+Housheng&rft.au=Luo%2C+Hui&rft.date=2023-09-01&rft.pub=Elsevier+Inc&rft.issn=0016-0032&rft.eissn=1879-2693&rft.volume=360&rft.issue=14&rft.spage=10564&rft.epage=10581&rft_id=info:doi/10.1016%2Fj.jfranklin.2023.08.010&rft.externalDocID=S001600322300501X
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0016-0032&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0016-0032&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0016-0032&client=summon