{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T11:50:14Z","timestamp":1780401014307,"version":"3.54.1"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Science and Technology Innovation 2030\u2014\u201cNew Generation Artificial Intelligence\u201d Major Project","award":["2018AAA0102301"],"award-info":[{"award-number":["2018AAA0102301"]}]},{"name":"Science and Technology Innovation 2030\u2014\u201cNew Generation Artificial Intelligence\u201d Major Project","award":["2018AAA0100302"],"award-info":[{"award-number":["2018AAA0100302"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61673025"],"award-info":[{"award-number":["61673025"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61375119"],"award-info":[{"award-number":["61375119"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Basic Research Development Plan (973 Plan) Project of China","doi-asserted-by":"publisher","award":["2015CB352302"],"award-info":[{"award-number":["2015CB352302"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2022,1]]},"DOI":"10.1109\/tcyb.2020.2979803","type":"journal-article","created":{"date-parts":[[2020,3,27]],"date-time":"2020-03-27T19:52:46Z","timestamp":1585338766000},"page":"252-264","source":"Crossref","is-referenced-by-count":14,"title":["Attentive Relational State Representation in Decentralized Multiagent Reinforcement Learning"],"prefix":"10.1109","volume":"52","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1092-2864","authenticated-orcid":false,"given":"Xiangyu","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8243-4731","authenticated-orcid":false,"given":"Ying","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2015.2504350"},{"key":"ref3","first-page":"32","article-title":"The complexity of decentralized control of Markov decision processes","volume-title":"Proc. 16th Conf. Uncertainty Artif. Intell. (UAI)","author":"Bernstein"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.dt.2013.03.001"},{"key":"ref5","first-page":"43","article-title":"Empirical analysis of predictive algorithms for collaborative filtering","volume-title":"Proc. 14th Conf. Uncertainty Artif. Intell. (UAI)","author":"Breese"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2904742"},{"key":"ref7","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Veli\u010dkovi\u0107"},{"key":"ref8","first-page":"746","article-title":"The dynamics of reinforcement learning in cooperative multiagent systems","volume-title":"Proc. 15th Nat. Conf. Artif. Intell. 10th Innov. Appl. Artif. Intell. Conf. (AAAI)","author":"Claus"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2424257"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref11","first-page":"1146","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","volume-title":"Proc. 34th Int. Conf. Mach. Learn. (ICML)","author":"Foerster"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2006.02.006"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2018.01.002"},{"key":"ref14","first-page":"227","article-title":"Coordinated reinforcement learning","volume-title":"Proc. 19th Int. Conf. Mach. Learn. (ICML)","author":"Guestrin"},{"key":"ref15","first-page":"5867","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","volume-title":"Proc. 35th Int. Conf. Mach. Learn. (ICML)","author":"Zhang"},{"key":"ref16","first-page":"2681","article-title":"Deep decentralized multi-task multi-agent reinforcement learning under partial observability","volume-title":"Proc. 34th Int. Conf. Mach. Learn. (ICML)","author":"Omidshafiei"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2402192"},{"key":"ref18","first-page":"6382","article-title":"Multi-agent actor\u2013critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 30th Annu. Conf. Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref20","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"Proc. 17th Int. Conf. Auton. Agents MultiAgent Syst. (AAMAS)","author":"Sunehag"},{"key":"ref21","volume-title":"ACCNET: Actor-coordinator-critic net \u2018learning-to-communicate\u2019 with deep multi-agent reinforcement learning","author":"Mao","year":"2017"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref23","first-page":"2244","article-title":"Learning multiagent communication with backpropagation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 29th Annu. Conf. Neural Inf. Process. Syst.","author":"Sukhbaatar"},{"key":"ref24","first-page":"5567","article-title":"Mean field multi-agent reinforcement learning","volume-title":"Proc. 35th Int. Conf. Mach. Learn. (ICML)","author":"Yang"},{"key":"ref25","first-page":"1","article-title":"Deep reinforcement learning for swarm systems","volume":"20","author":"H\u00fcttenrauch","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref26","article-title":"Multiagent bidirectionally-coordinated nets for learning to play StarCraft combat games","volume":"abs\/1703.10069","author":"Peng","year":"2017","journal-title":"CoRR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00533-7_6"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19457-3_1"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref30","first-page":"7265","article-title":"Learning attentional communication for multi-agent cooperation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 31st Annu. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Jiang"},{"key":"ref31","first-page":"1538","article-title":"TarMAC: Targeted multi-agent communication","volume-title":"Proc. 36th Int. Conf. Mach. Learn. (ICML)","author":"Das"},{"key":"ref32","first-page":"1108","article-title":"Modelling the dynamic joint policy of teammates with attention multi-agent DDPG","volume-title":"Proc. 18th Int. Conf. Auton. Agents MultiAgent Syst. (AAMAS)","author":"Mao"},{"key":"ref33","first-page":"2698","article-title":"VAIN: Attentional multi-agent predictive modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 30th Annu. Conf. Neural Inf. Process. Syst.","author":"Hoshen"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2419263"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2549034"},{"key":"ref36","article-title":"Graph representation learning: A survey","volume":"abs\/1909.00958","author":"Chen","year":"2019","journal-title":"CoRR"},{"key":"ref37","article-title":"Multi-agent game abstraction via graph attention neural network","volume":"abs\/1911.10715","author":"Liu","year":"2019","journal-title":"CoRR"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref39","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 30th Annu. Conf. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022676722315"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref42","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. 33nd Int. Conf. Mach. Learn. (ICML)","author":"Wang"},{"key":"ref43","article-title":"Fast and accurate deep network learning by exponential linear units (ELUS)","volume-title":"Proc. 4th Int. Conf. Learn. Represent. (ICLR)","author":"Clevert"},{"key":"ref44","article-title":"Prioritized experience replay","volume-title":"Proc. 4th Int. Conf. Learn. Represent. (ICLR)","author":"Schaul"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210009"},{"key":"ref46","first-page":"330","article-title":"Multi-agent reinforcement learning: Independent versus cooperative agents","volume-title":"Proc. 10th Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref47","first-page":"2204","article-title":"Recurrent models of visual attention","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 27th Annu. Conf. Neural Inf. Process. Syst.","author":"Mnih"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2005.1545539"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2013.2286295"},{"key":"ref50","article-title":"StarCraft II: A new challenge for reinforcement learning","volume":"abs\/1708.04782","author":"Vinyalso","year":"2017","journal-title":"CoRR"},{"key":"ref51","article-title":"TStarBots: Defeating the cheating level Builtin AI in StarCraft II in the full game","volume":"abs\/1809.07193","author":"Sun","year":"2018","journal-title":"CoRR"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v14i1.13033"},{"key":"ref53","first-page":"1804","article-title":"Opponent modeling in deep reinforcement learning","volume-title":"Proc. 33nd Int. Conf. Mach. Learn. (ICML)","author":"He"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/9678110\/09049415.pdf?arnumber=9049415","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T22:29:09Z","timestamp":1704839349000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9049415\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1]]},"references-count":53,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2020.2979803","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1]]}}}