{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T02:44:28Z","timestamp":1775529868966,"version":"3.50.1"},"reference-count":80,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Key R&D Program of China","award":["2020YFB1313300"],"award-info":[{"award-number":["2020YFB1313300"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2022M721838"],"award-info":[{"award-number":["2022M721838"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2022A1515110787"],"award-info":[{"award-number":["2022A1515110787"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Robot."],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1109\/tro.2023.3257541","type":"journal-article","created":{"date-parts":[[2023,4,12]],"date-time":"2023-04-12T17:37:05Z","timestamp":1681321025000},"page":"2603-2622","source":"Crossref","is-referenced-by-count":35,"title":["Asymmetric Self-Play-Enabled Intelligent Heterogeneous Multirobot Catching System Using Deep Multiagent Reinforcement Learning"],"prefix":"10.1109","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3324-4418","authenticated-orcid":false,"given":"Yuan","family":"Gao","sequence":"first","affiliation":[{"name":"Shenzhen Institute of Artificial Intelligence and Robotics for Society, The Chinese University of Hong Kong, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0617-5031","authenticated-orcid":false,"given":"Junfeng","family":"Chen","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Artificial Intelligence and Robotics for Society, The Chinese University of Hong Kong, Shenzhen, China"}]},{"given":"Xi","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9819-088X","authenticated-orcid":false,"given":"Chongyang","family":"Wang","sequence":"additional","affiliation":[{"name":"University College London, London, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1911-4361","authenticated-orcid":false,"given":"Junjie","family":"Hu","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Artificial Intelligence and Robotics for Society, The Chinese University of Hong Kong, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7071-7184","authenticated-orcid":false,"given":"Fuqin","family":"Deng","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Artificial Intelligence and Robotics for Society, The Chinese University of Hong Kong, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6363-1446","authenticated-orcid":false,"given":"Tin Lun","family":"Lam","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Artificial Intelligence and Robotics for Society, The Chinese University of Hong Kong, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3303848"},{"key":"ref57","article-title":"Qplex: Duplex dueling multi-agent Q-learning","author":"wang","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/socs.v10i1.18501"},{"key":"ref56","first-page":"4295","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2965855"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref58","article-title":"On the use and misuse of absorbing states in multi-agent reinforcement learning","author":"cohen","year":"2022"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487173"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593702"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF38699.2020.9389145"},{"key":"ref55","article-title":"Dota 2 with large scale deep reinforcement learning","author":"berner","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1002\/rob.22014"},{"key":"ref54","first-page":"1","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/AMC.2016.7496328"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/s16071018"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461113"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/5781591"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2020.2990921"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2017.2752302"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2014.11.006"},{"key":"ref47","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3390\/s18103391"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.01.092"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2019.01.007"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3390\/s19061474"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017643"},{"key":"ref8","article-title":"Autonomous VTOL-UAV docking system for heterogeneous multirobot team","volume":"70","author":"narv\u00e1ez","year":"2020","journal-title":"IEEE Trans Instrum Meas"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3007468"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20915-5_59"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1243\/095965105X9470"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3143013"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3067859"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2013.2252996"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/11810.001.0001"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1138-y"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2849588"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3011912"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793609"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2011.6083114"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2018.03.012"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980114"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2941178"},{"key":"ref75","article-title":"Unity: A general platform for intelligent agents","author":"juliani","year":"2018"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2010.03.013"},{"key":"ref74","article-title":"Minatar: An atari-inspired testbed for thorough and reproducible reinforcement learning experiments","author":"young","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2837226"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793865"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"4435","DOI":"10.1109\/LRA.2018.2871803","article-title":"Introduction to the special issue on precision agricultural robotics and autonomous farming technologies","volume":"3","author":"ahn","year":"2018","journal-title":"IEEE Robot Automat Lett"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2016.2631593"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17340"},{"key":"ref39","author":"ashby","year":"1961","journal-title":"An Introduction to Cybernetics"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.13164\/mendel.2019.1.111"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2016.2578312"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2016.2633248"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/VTCFall.2016.7881122"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3027422"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0277(93)90058-4"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106312"},{"key":"ref67","first-page":"1","article-title":"Intrinsic motivation and automatic curricula via asymmetric self-play","author":"sukhbaatar","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref26","article-title":"Efficient multi-robot exploration with energy constraint based on optimal transport theory","author":"kabir","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-019-01081-3"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref20","article-title":"Blockchain-powered collaboration in heterogeneous swarms of robots","author":"queralta","year":"2019"},{"key":"ref64","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2019.8848006"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.2967656"},{"key":"ref66","article-title":"Asymmetric self-play for automatic goal discovery in robotic manipulation","author":"openai","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1186\/s40064-016-3027-2"},{"key":"ref65","article-title":"Generating automatic curricula via self-supervised active domain randomization","author":"raparthy","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2891475"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3044834"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487748"},{"key":"ref60","first-page":"1","article-title":"Credit assignment for collective multiagent RL with global rewards","volume":"31","author":"nguyen","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1147\/rd.116.0601"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2922493"}],"container-title":["IEEE Transactions on Robotics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8860\/10214173\/10101687.pdf?arnumber=10101687","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T18:16:08Z","timestamp":1693246568000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10101687\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8]]},"references-count":80,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tro.2023.3257541","relation":{},"ISSN":["1552-3098","1941-0468"],"issn-type":[{"value":"1552-3098","type":"print"},{"value":"1941-0468","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8]]}}}