Distributed multi-agent deep reinforcement learning for cooperative multi-robot pursuit
As a popular research topic in the area of distributed artificial intelligence, the multi-robot pursuit problem is widely used as a testbed for evaluating coordinated and cooperative strategies in multi-robot systems. This study the problem of multi-robot pursuit game using reinforcement learning (R...
Saved in:
| Published in: | Journal of engineering (Stevenage, England) Vol. 2020; no. 13; pp. 499 - 504 |
|---|---|
| Main Authors: | , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
The Institution of Engineering and Technology
01.07.2020
|
| Subjects: | |
| ISSN: | 2051-3305, 2051-3305 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | As a popular research topic in the area of distributed artificial intelligence, the multi-robot pursuit problem is widely used as a testbed for evaluating coordinated and cooperative strategies in multi-robot systems. This study the problem of multi-robot pursuit game using reinforcement learning (RL) techniques is studied. Unlike most existing studies that apply fully centralised deep RL methods based on the centralised-learning and decentralised-execution scheme, the authors propose a fully decentralised multi-agent deep RL approach by modelling each agent as an individual deep RL agent that has its own individual learning system (i.e. individual action-value function, individual leaning update process, and individual action output). To realise coordination among agents, the limited information of other environmental agents is used as input of the learning process. Experimental results show that both distributed and centralised approaches can ultimately solve the pursuit-evasion problem in different dimensions, but the learning efficiency and coordination performance of the proposed distributed approach are much better than the traditional centralised approach. |
|---|---|
| AbstractList | As a popular research topic in the area of distributed artificial intelligence, the multi‐robot pursuit problem is widely used as a testbed for evaluating coordinated and cooperative strategies in multi‐robot systems. This study the problem of multi‐robot pursuit game using reinforcement learning (RL) techniques is studied. Unlike most existing studies that apply fully centralised deep RL methods based on the centralised‐learning and decentralised‐execution scheme, the authors propose a fully decentralised multi‐agent deep RL approach by modelling each agent as an individual deep RL agent that has its own individual learning system (i.e. individual action‐value function, individual leaning update process, and individual action output). To realise coordination among agents, the limited information of other environmental agents is used as input of the learning process. Experimental results show that both distributed and centralised approaches can ultimately solve the pursuit‐evasion problem in different dimensions, but the learning efficiency and coordination performance of the proposed distributed approach are much better than the traditional centralised approach. |
| Author | Chen, Yatong Yu, Chao Li, Yangning Dong, Yinzhao |
| Author_xml | – sequence: 1 givenname: Chao surname: Yu fullname: Yu, Chao email: cy496@dlut.edu.cn organization: 1School of Data and Computer Science, Sun Yat-Sen University, 510006, Guangzhou, People's Republic of China – sequence: 2 givenname: Yinzhao surname: Dong fullname: Dong, Yinzhao organization: 2School of Computer Science and Technology, Dalian University of Technology, Dalian 116024, People's Republic of China – sequence: 3 givenname: Yangning surname: Li fullname: Li, Yangning organization: 2School of Computer Science and Technology, Dalian University of Technology, Dalian 116024, People's Republic of China – sequence: 4 givenname: Yatong surname: Chen fullname: Chen, Yatong organization: 2School of Computer Science and Technology, Dalian University of Technology, Dalian 116024, People's Republic of China |
| BookMark | eNp9kD1PwzAQhi1UJErpyJ6VIeVsN3EyQmn5UCWWIsbIcS6Vq9SObAfUf0-idkBIZbrT6X3uTs81GRlrkJBbCjMK8_x-Z3HGgOYzygAuyJhBQmPOIRn96q_I1PsdAFA-ZzCnY_L5pH1wuuwCVtG-a4KO5RZNiCrENnKoTW2dwv0walA6o8026keRsrZFJ4P-whPnbGlD1HbOdzrckMtaNh6npzohH6vlZvESr9-fXxcP61ixTEDMyiRFJVIQXFHEnNWcK8XLpEylYLUCLpSASuaYKSHTpMqEwjQDIUXGKUM-Ify4VznrvcO6UDr0X1kTnNRNQaEY9BS9nmLQUwx6eir-Q7VO76U7nM2nx_y3bvDwf7jYvC3Z4wo4sAG8O4IaQx_rnOllnDnyAySaiE0 |
| CitedBy_id | crossref_primary_10_1016_j_eswa_2024_126029 crossref_primary_10_1109_TCYB_2021_3080044 crossref_primary_10_3390_s23073625 crossref_primary_10_1109_TNNLS_2021_3124466 crossref_primary_10_1016_j_actaastro_2022_05_057 crossref_primary_10_1109_TASE_2024_3420094 crossref_primary_10_1109_TCDS_2025_3540071 crossref_primary_10_1109_TRO_2023_3263459 crossref_primary_10_1016_j_ifacol_2023_10_1100 crossref_primary_10_1109_LCSYS_2021_3070850 crossref_primary_10_1109_COMST_2021_3086014 crossref_primary_10_3389_fpls_2022_898183 crossref_primary_10_1109_LRA_2022_3188904 |
| Cites_doi | 10.1038/nature16961 10.1609/aaai.v30i1.10295 10.1007/BF00992698 10.1109/TRA.2002.804040 10.1109/TNNLS.2015.2403394 10.1177/0278364910369949 10.1109/JPROC.2006.887293 10.1109/TITS.2019.2893683 10.1109/FUZZ-IEEE.2016.7737744 10.1609/aaai.v32i1.11371 10.1109/TCYB.2014.2387277 10.1016/B978-1-55860-307-3.50049-6 10.1016/j.mcm.2009.06.011 10.1109/TCYB.2014.2306919 10.1109/TSMCC.2012.2218595 10.1038/nature14236 10.1109/TSMCC.2007.913919 |
| ContentType | Journal Article |
| Copyright | 2021 The Institution of Engineering and Technology |
| Copyright_xml | – notice: 2021 The Institution of Engineering and Technology |
| DBID | IDLOA 24P AAYXX CITATION |
| DOI | 10.1049/joe.2019.1200 |
| DatabaseName | IET Digital Library Open Access Wiley Online Library Open Access CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | CrossRef |
| Database_xml | – sequence: 1 dbid: 24P name: Wiley Online Library Open Access url: https://authorservices.wiley.com/open-science/open-access/browse-journals.html sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 2051-3305 |
| EndPage | 504 |
| ExternalDocumentID | 10_1049_joe_2019_1200 TJE2BF03020 |
| Genre | article |
| GrantInformation_xml | – fundername: Ministry of Military Equipment Development of China funderid: 61403120203 – fundername: Dalian High‐Level Talent Innovation Support Program funderid: 2017RQ008 – fundername: Dalian Science and Technology Innovation Fund funderid: 2018J12GX046 – fundername: Joint Key Program of National Natural Science Foundation of China and Liaoning Province funderid: U1808206 |
| GroupedDBID | 24P 5VS AAJGR ADACO ADBBV ALMA_UNASSIGNED_HOLDINGS BCNDV BFFAM GROUPED_DOAJ IDLOA KQ8 OCL OK1 RIE RIG RNS RUI 0R~ 1OC AAHJG ABJCF ABQXS ACCMX ACESK ACXQS AFKRA ARAPS AVUZU BENPR BGLVJ CCPQU EBS HCIFZ IAO IGS IPNFZ ITC M43 M7S M~E PIMPY PTHSS ROL AAMMB AAYXX ADMLS AEFGJ AFFHD AGXDD AIDQK AIDYY CITATION PHGZM PHGZT PQGLB WIN |
| ID | FETCH-LOGICAL-c2870-2b56ec76073c1ee92f33cc3b5b6a72fc037c70da9e8c7a65d87ce6807a78312e3 |
| IEDL.DBID | 24P |
| ISICitedReferencesCount | 36 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000565270600041&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2051-3305 |
| IngestDate | Wed Oct 29 21:32:51 EDT 2025 Tue Nov 18 20:59:19 EST 2025 Wed Jan 22 16:30:42 EST 2025 Tue Jan 05 21:44:04 EST 2021 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 13 |
| Keywords | pursuit-evasion problem multi-agent systems individual leaning update process distributed control game theory multirobot pursuit game deep RL methods multi-robot systems decentralised-execution scheme distributed artificial intelligence learning systems environmental agents individual action output distributed multiagent deep reinforcement learning multiagent deep RL approach learning (artificial intelligence) control engineering computing multirobot systems |
| Language | English |
| License | Attribution |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c2870-2b56ec76073c1ee92f33cc3b5b6a72fc037c70da9e8c7a65d87ce6807a78312e3 |
| OpenAccessLink | https://onlinelibrary.wiley.com/doi/abs/10.1049%2Fjoe.2019.1200 |
| PageCount | 6 |
| ParticipantIDs | crossref_primary_10_1049_joe_2019_1200 crossref_citationtrail_10_1049_joe_2019_1200 iet_journals_10_1049_joe_2019_1200 wiley_primary_10_1049_joe_2019_1200_TJE2BF03020 |
| ProviderPackageCode | IDLOA RUI |
| PublicationCentury | 2000 |
| PublicationDate | 20200700 July 2020 2020-07-00 |
| PublicationDateYYYYMMDD | 2020-07-01 |
| PublicationDate_xml | – month: 7 year: 2020 text: 20200700 |
| PublicationDecade | 2020 |
| PublicationTitle | Journal of engineering (Stevenage, England) |
| PublicationYear | 2020 |
| Publisher | The Institution of Engineering and Technology |
| Publisher_xml | – name: The Institution of Engineering and Technology |
| References | Su, Z.B.; Lu, J.L.; Tong, L. (C19) 2004; 5 Hollinger, G.; Singh, S.; Kehagias, A. (C17) 2010; 29 Yu, C.; Zhang, M.; Ren, F. (C23) 2014; 44 Silver, D.; Huang, A.; Maddison, C.J. (C3) 2015; 529 Busoniu, L.; Babuska, R.; De Schutter, B. (C5) 2008; 38 Mnih, V.; Kavukcuoglu, K.; Silver, D. (C6) 2015; 518 Kehagias, A.; Hollinger, G.; Singh, S. (C16) 2009; 50 Yu, C.; Wang, X.; Xu, X. (C20) 2020; 21 Grondman, I.; Busoniu, L.; Lopes, G.A. (C30) 2012; 42 Vidal, R.; Shakernia, O.; Kim, H.J. (C14) 2002; 18 Yu, C.; Zhang, M.; Ren, F. (C21) 2015; 26 Olfati-Saber, R.; Fax, J.A; Murray, R.M. (C4) 2007; 95 Yu, C.; Zhang, M.; Ren, F. (C22) 2015; 45 Isaacs, R.; Philip, R. (C12) 1966; 17 Watkins Christopher, J.C.H.; Dayan, P. (C25) 1992; 8 2015; 45 2015; 26 1992; 8 1966; 17 2002; 18 2009; 50 2010; 29 2008; 38 1976 2018 2015; 529 2015; 518 2017 2004; 5 2016 2015 1993 2007; 95 2020; 21 2014; 44 2012; 42 e_1_2_8_28_1 e_1_2_8_29_1 Parsons D.T. (e_1_2_8_14_1) 1976 e_1_2_8_24_1 e_1_2_8_25_1 e_1_2_8_26_1 e_1_2_8_27_1 Su Z.B. (e_1_2_8_20_1) 2004; 5 e_1_2_8_3_1 e_1_2_8_5_1 e_1_2_8_4_1 e_1_2_8_7_1 e_1_2_8_6_1 e_1_2_8_9_1 e_1_2_8_8_1 e_1_2_8_21_1 e_1_2_8_22_1 e_1_2_8_23_1 Isaacs R. (e_1_2_8_13_1) 1966; 17 e_1_2_8_17_1 e_1_2_8_18_1 e_1_2_8_19_1 e_1_2_8_15_1 e_1_2_8_16_1 e_1_2_8_10_1 e_1_2_8_31_1 Sutton R.S. (e_1_2_8_2_1) 2018 e_1_2_8_11_1 e_1_2_8_12_1 e_1_2_8_30_1 |
| References_xml | – volume: 18 start-page: 662 issue: 5 year: 2002 end-page: 669 ident: C14 article-title: Probabilistic pursuit-evasion games: theory, implementation, and experimental evaluation publication-title: IEEE Trans. Robotics Autom. – volume: 8 start-page: 279 issue: 3–4 year: 1992 end-page: 292 ident: C25 article-title: Q-learning publication-title: Mach. Learn. – volume: 50 start-page: 1305 issue: 9 year: 2009 end-page: 1317 ident: C16 article-title: A graph search algorithm for indoor pursuit/evasion publication-title: Math. Comput. Model. – volume: 45 start-page: 2853 issue: 12 year: 2015 end-page: 2867 ident: C22 article-title: Multiagent learning of coordination in loosely coupled multiagent systems publication-title: IEEE Trans. Cybern. – volume: 518 start-page: 529 issue: 7540 year: 2015 ident: C6 article-title: Human-level control through deep reinforcement learning publication-title: Nature – volume: 44 start-page: 2342 issue: 12 year: 2014 end-page: 2355 ident: C23 article-title: Collective learning for the emergence of social norms in networked multiagent systems publication-title: IEEE Trans. Cybern. – volume: 95 start-page: 215 issue: 1 year: 2007 end-page: 233 ident: C4 article-title: Consensus and cooperation in networked multi-agent systems publication-title: Proc. IEEE – volume: 42 start-page: 1291 issue: 6 year: 2012 end-page: 1307 ident: C30 article-title: A survey of actor-critic reinforcement learning: standard and natural policy gradients publication-title: IEEE Trans. Syst. Man Cybern., C – volume: 529 start-page: 484 issue: 7587 year: 2015 end-page: 489 ident: C3 article-title: Mastering the game of Go with deep neural networks and tree search publication-title: Nature – volume: 5 start-page: 403 issue: 8 year: 2004 end-page: 406 ident: C19 article-title: Strategy of cooperative hunting by multiple Mobile robots publication-title: J. Beijing Inst. Technol. – volume: 17 start-page: 60 issue: 2 year: 1966 end-page: 60 ident: C12 article-title: Differential games: a mathematical theory with applications to warfare and pursuit publication-title: Control Opt. – volume: 38 start-page: 156 issue: 2 year: 2008 end-page: 172 ident: C5 article-title: A comprehensive survey of multiagent reinforcement learning publication-title: IEEE Trans. Syst. Man Cybern.-C, Appl. Rev. – volume: 26 start-page: 3083 issue: 12 year: 2015 end-page: 3096 ident: C21 article-title: Emotional multiagent reinforcement learning in spatial social dilemmas publication-title: IEEE Trans. Neural Netw. Learn. Syst. – volume: 21 start-page: 735 issue: 2 year: 2020 end-page: 748 ident: C20 article-title: Distributed multiagent coordinated learning for autonomous driving in highways based on dynamic coordination graphs publication-title: IEEE Trans. Intell. Transp. Syst. – volume: 29 start-page: 1088 issue: 8 year: 2010 end-page: 1105 ident: C17 article-title: Improving the efficiency of clearing with multi-agent teams publication-title: Int. J. Robotics Res. – volume: 518 start-page: 529 issue: 7540 year: 2015 article-title: Human‐level control through deep reinforcement learning publication-title: Nature – start-page: 2085 year: 2017 end-page: 2087 article-title: Value‐decomposition networks for cooperative multi‐agent learning – start-page: 426 year: 1976 end-page: 441 – start-page: 330 year: 1993 end-page: 337 article-title: Multi‐agent reinforcement learning: independent vs. Cooperative agents – volume: 8 start-page: 279 issue: 3–4 year: 1992 end-page: 292 article-title: Q‐learning publication-title: Mach. Learn. – start-page: 1995 year: 2016 end-page: 2003 article-title: Dueling network architectures for deep reinforcement learning – volume: 95 start-page: 215 issue: 1 year: 2007 end-page: 233 article-title: Consensus and cooperation in networked multi‐agent systems publication-title: Proc. IEEE – start-page: 618 year: 2016 end-page: 625 article-title: Game of drones: UAV pursuit‐evasion game with type‐2 fuzzy logic controllers tuned by reinforcement learning – volume: 21 start-page: 735 issue: 2 year: 2020 end-page: 748 article-title: Distributed multiagent coordinated learning for autonomous driving in highways based on dynamic coordination graphs publication-title: IEEE Trans. Intell. Transp. Syst. – volume: 18 start-page: 662 issue: 5 year: 2002 end-page: 669 article-title: Probabilistic pursuit‐evasion games: theory, implementation, and experimental evaluation publication-title: IEEE Trans. Robotics Autom. – volume: 26 start-page: 3083 issue: 12 year: 2015 end-page: 3096 article-title: Emotional multiagent reinforcement learning in spatial social dilemmas publication-title: IEEE Trans. Neural Netw. Learn. Syst. – start-page: 464 year: 2017 end-page: 473 article-title: Multi‐agent reinforcement learning in sequential social dilemmas – volume: 42 start-page: 1291 issue: 6 year: 2012 end-page: 1307 article-title: A survey of actor‐critic reinforcement learning: standard and natural policy gradients publication-title: IEEE Trans. Syst. Man Cybern., C – year: 2018 – volume: 529 start-page: 484 issue: 7587 year: 2015 end-page: 489 article-title: Mastering the game of Go with deep neural networks and tree search publication-title: Nature – volume: 45 start-page: 2853 issue: 12 year: 2015 end-page: 2867 article-title: Multiagent learning of coordination in loosely coupled multiagent systems publication-title: IEEE Trans. Cybern. – volume: 5 start-page: 403 issue: 8 year: 2004 end-page: 406 article-title: Strategy of cooperative hunting by multiple Mobile robots publication-title: J. Beijing Inst. Technol. – volume: 17 start-page: 60 issue: 2 year: 1966 end-page: 60 article-title: Differential games: a mathematical theory with applications to warfare and pursuit publication-title: Control Opt. – year: 2018 article-title: MAgent: a many‐agent reinforcement learning platform for artificial collective intelligence – start-page: 6379 year: 2017 end-page: 6390 article-title: Multi‐agent actor‐critic for mixed cooperative‐competitive environments – volume: 38 start-page: 156 issue: 2 year: 2008 end-page: 172 article-title: A comprehensive survey of multiagent reinforcement learning publication-title: IEEE Trans. Syst. Man Cybern.‐C, Appl. Rev. – start-page: 1889 year: 2015 end-page: 1897 article-title: Trust region policy optimization – volume: 50 start-page: 1305 issue: 9 year: 2009 end-page: 1317 article-title: A graph search algorithm for indoor pursuit/evasion publication-title: Math. Comput. Model. – year: 2016 article-title: Collaboration in Ad hoc teamwork: ambiguous tasks, roles, and communication – year: 2015 article-title: Deep recurrent Q‐learning for partially observable MDPs – year: 2017 – volume: 29 start-page: 1088 issue: 8 year: 2010 end-page: 1105 article-title: Improving the efficiency of clearing with multi‐agent teams publication-title: Int. J. Robotics Res. – volume: 44 start-page: 2342 issue: 12 year: 2014 end-page: 2355 article-title: Collective learning for the emergence of social norms in networked multiagent systems publication-title: IEEE Trans. Cybern. – year: 2015 article-title: Deep reinforcement learning with double Q‐learning – ident: e_1_2_8_4_1 doi: 10.1038/nature16961 – ident: e_1_2_8_27_1 doi: 10.1609/aaai.v30i1.10295 – ident: e_1_2_8_11_1 – ident: e_1_2_8_26_1 doi: 10.1007/BF00992698 – ident: e_1_2_8_15_1 doi: 10.1109/TRA.2002.804040 – ident: e_1_2_8_3_1 – ident: e_1_2_8_22_1 doi: 10.1109/TNNLS.2015.2403394 – ident: e_1_2_8_28_1 – ident: e_1_2_8_18_1 doi: 10.1177/0278364910369949 – volume-title: Reinforcement learning: an Introduction year: 2018 ident: e_1_2_8_2_1 – ident: e_1_2_8_5_1 doi: 10.1109/JPROC.2006.887293 – ident: e_1_2_8_10_1 – start-page: 426 volume-title: Theory and Applications of Graphs. Lecture Notes in Mathematics year: 1976 ident: e_1_2_8_14_1 – ident: e_1_2_8_21_1 doi: 10.1109/TITS.2019.2893683 – ident: e_1_2_8_16_1 doi: 10.1109/FUZZ-IEEE.2016.7737744 – ident: e_1_2_8_30_1 doi: 10.1609/aaai.v32i1.11371 – ident: e_1_2_8_23_1 doi: 10.1109/TCYB.2014.2387277 – ident: e_1_2_8_19_1 – ident: e_1_2_8_25_1 doi: 10.1016/B978-1-55860-307-3.50049-6 – ident: e_1_2_8_17_1 doi: 10.1016/j.mcm.2009.06.011 – ident: e_1_2_8_24_1 doi: 10.1109/TCYB.2014.2306919 – ident: e_1_2_8_8_1 – ident: e_1_2_8_31_1 doi: 10.1109/TSMCC.2012.2218595 – ident: e_1_2_8_7_1 doi: 10.1038/nature14236 – volume: 17 start-page: 60 issue: 2 year: 1966 ident: e_1_2_8_13_1 article-title: Differential games: a mathematical theory with applications to warfare and pursuit publication-title: Control Opt. – volume: 5 start-page: 403 issue: 8 year: 2004 ident: e_1_2_8_20_1 article-title: Strategy of cooperative hunting by multiple Mobile robots publication-title: J. Beijing Inst. Technol. – ident: e_1_2_8_12_1 – ident: e_1_2_8_9_1 – ident: e_1_2_8_29_1 – ident: e_1_2_8_6_1 doi: 10.1109/TSMCC.2007.913919 |
| SSID | ssj0001342041 |
| Score | 2.3224165 |
| Snippet | As a popular research topic in the area of distributed artificial intelligence, the multi-robot pursuit problem is widely used as a testbed for evaluating... As a popular research topic in the area of distributed artificial intelligence, the multi‐robot pursuit problem is widely used as a testbed for evaluating... |
| SourceID | crossref wiley iet |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 499 |
| SubjectTerms | control engineering computing decentralised‐execution scheme deep RL methods distributed artificial intelligence distributed control distributed multiagent deep reinforcement learning environmental agents game theory individual action output individual leaning update process learning (artificial intelligence) learning systems multiagent deep RL approach multirobot pursuit game multirobot systems multi‐agent systems multi‐robot systems pursuit‐evasion problem The 3rd Asian Conference on Artificial Intelligence Technology (ACAIT 2019) |
| Title | Distributed multi-agent deep reinforcement learning for cooperative multi-robot pursuit |
| URI | http://digital-library.theiet.org/content/journals/10.1049/joe.2019.1200 https://onlinelibrary.wiley.com/doi/abs/10.1049%2Fjoe.2019.1200 |
| Volume | 2020 |
| WOSCitedRecordID | wos000565270600041&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2051-3305 dateEnd: 20241231 omitProxy: false ssIdentifier: ssj0001342041 issn: 2051-3305 databaseCode: DOA dateStart: 20130101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2051-3305 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001342041 issn: 2051-3305 databaseCode: M~E dateStart: 20130101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVWIB databaseName: Wiley Free Archive customDbUrl: eissn: 2051-3305 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001342041 issn: 2051-3305 databaseCode: WIN dateStart: 20130101 isFulltext: true titleUrlDefault: https://onlinelibrary.wiley.com providerName: Wiley-Blackwell – providerCode: PRVWIB databaseName: Wiley Online Library Open Access customDbUrl: eissn: 2051-3305 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001342041 issn: 2051-3305 databaseCode: 24P dateStart: 20130101 isFulltext: true titleUrlDefault: https://authorservices.wiley.com/open-science/open-access/browse-journals.html providerName: Wiley-Blackwell |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV29TsMwELZoYYCBf0T5qSyEmAgkthMnI4JWgKDqUKASQ-Q4F1QJNVGaMiIegWfkSbCdUOhQJMTiIbKt6Hxn-85334fQoY7kR8RU4wTCYoKCFTCHWS4jceBLwaSpcr2_4Z2O3-8H3YrnVNfClPgQk4CbtgyzX2sDF1HJQqIutdrIU41y6QQnjlroGpp3HMq1WhPW_Q6yUEZsw15JlPJZynd3K5xNNcfp1AxT51JtAMX0bdUcN-2Vf__oKlqubpr4rFSNNTQHw3W09AN_cAM9XmjYXM14BTE2qYUfb-9CF1vhGCDDORhcVWlCiLgimHjC6hOWaZpBiRo-GZmnUVrgbJyPxoNiE921W73zS6tiW7Ckfuy0SOR6ILmnbF46AAFJKJWSRm7kCU4SaVMuuR2LAHzJhefGPpfg-TYX3KcOAbqF6sN0CNsIJy6A8qs8BnHCgLiRsu3Y04musYx8mjTQ8ZesQ1lBkWtGjOfQPImzIFQyC7XMQi2zBjqadM9KDI5ZHQ_UwoWVFY5mdTo1q_X7VGHvukVMdjyxd_48YhctEu2Xm7TePVQv8jHsowX5UgxGedPoaNN4_6q9fW2p9uGq8wlmt-tM |
| linkProvider | Wiley-Blackwell |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LT8MwDI7YQAIOvBHjGSHEibI2SZv2iGATjzHtMNAkDlWbumgIrVXXceYn8Bv5JSRpGdthSIhr5ViVY8exY39G6ERl8kOiu3G8wGABBcNjFjNsRiLPFQETusv1scXbbbfX8zoTXfwFPsQ44aYsQ5_XysBVQroIOJkCyXxJFMyl5Z1bcqcraJ5JT6NmGBDW-cmyUEZMPb6SSO0zZPBul0Cbkkd9isOUY6r0IZ--rmp_01z9_5-uoZXyrokvCuVYR3Mw2EDLEwiEm-jpSgHnqplXEGFdXPj5_hGodiscAaQ4A42sKnQSEZcjJp6x_IRFkqRQ4IaPV2ZJmOQ4HWXDUT_fQg_NRvfy2ijnLRhCPXcaJLQdENyRVi8sAI_ElApBQzt0Ak5iYVIuuBkFHriCB44duVyA45o84C61CNBtVB0kA9hBOLYBZGTlMIhiBsQOpXVHjip1jUTo0riGzr6F7YsSjFzNxHj19aM483wpM1_JzFcyq6HTMXlaoHDMIjyWO-eXdjicRVTX2_U7K7972yC6Pp6Yu39ecYQWr7v3Lb91077bQ0tERem6yHcfVfNsBAdoQbzl_WF2qBX2C8PA6_k |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LT8MwDI5gIAQH3ojxjBDiRFmbpE17RGwTj2naAdAkDlWbuGgIrVXXceYn8Bv5JSRpGewAEuJaOVblRxI79meEjnUmPyamGyeILBZRsALmMMtlRAa-iJgwXa73Hd7t-v1-0PvWxV_iQ0wSbtozzH6tHRwymZQBJ9MgmU-phrl0gjNHaXoWzTFX7bMa25n1vrIslBHbjK8kyvosFby7FdCm4tGY4jB1MM0OoJi-rprzpr3y_z9dRcvVXROfl8axhmZguI6WviEQbqCHpgbO1TOvQGJTXPj--hbpdissATKcg0FWFSaJiKsRE49YfcIiTTMoccMnK_M0TgucjfPReFBsort26_bi0qrmLVhCP3daJHY9ENxTXi8cgIAklApBYzf2Ik4SYVMuuC2jAHzBI8-VPhfg-TaPuE8dAnQL1YbpELYRTlwAFVl5DGTCgLix8m7p6VJXKWKfJnV0-insUFRg5HomxnNoHsVZECqZhVpmoZZZHZ1MyLMSheMnwiOlubDyw9FPRA2jrt9ZhbfXLWLq44m98-cVh2ih12yHnavuzS5aJDpINzW-e6hW5GPYR_PipRiM8gNjrx-Dlut9 |
| 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=Distributed+multi-agent+deep+reinforcement+learning+for+cooperative+multi-robot+pursuit&rft.jtitle=Journal+of+engineering+%28Stevenage%2C+England%29&rft.au=Yu%2C+Chao&rft.au=Dong%2C+Yinzhao&rft.au=Li%2C+Yangning&rft.au=Chen%2C+Yatong&rft.date=2020-07-01&rft.pub=The+Institution+of+Engineering+and+Technology&rft.eissn=2051-3305&rft.volume=2020&rft.issue=13&rft.spage=499&rft.epage=504&rft_id=info:doi/10.1049%2Fjoe.2019.1200&rft.externalDocID=10_1049_joe_2019_1200 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2051-3305&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2051-3305&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2051-3305&client=summon |