{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T15:02:07Z","timestamp":1784646127671,"version":"3.55.0"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018AAA0102404"],"award-info":[{"award-number":["2018AAA0102404"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Strategic Priority Research Program of Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["XDA27030400"],"award-info":[{"award-number":["XDA27030400"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Youth Innovation Promotion Association of CAS","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2023,4]]},"DOI":"10.1109\/tnnls.2021.3105869","type":"journal-article","created":{"date-parts":[[2021,8,30]],"date-time":"2021-08-30T20:53:40Z","timestamp":1630356820000},"page":"2093-2104","source":"Crossref","is-referenced-by-count":43,"title":["UNMAS: Multiagent Reinforcement Learning for Unshaped Cooperative Scenarios"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7611-064X","authenticated-orcid":false,"given":"Jiajun","family":"Chai","sequence":"first","affiliation":[{"name":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weifan","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5384-423X","authenticated-orcid":false,"given":"Yuanheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8218-9633","authenticated-orcid":false,"given":"Dongbin","family":"Zhao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhe","family":"Ma","sequence":"additional","affiliation":[{"name":"X-Lab, The Second Academy of CASIC, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kewu","family":"Sun","sequence":"additional","affiliation":[{"name":"X-Lab, The Second Academy of CASIC, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jishiyu","family":"Ding","sequence":"additional","affiliation":[{"name":"X-Lab, The Second Academy of CASIC, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2012.2219061"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2894403"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICIST.2018.8426160"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2018.2823329"},{"key":"ref5","first-page":"4295","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rashid"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2018.8628682"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313433"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2018.2811376"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933962"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927869"},{"key":"ref11","first-page":"443","article-title":"Lenient multi-agent deep reinforcement learning","volume-title":"Proc. Int. Found. Auton. Agents Multiagent Syst.","author":"Palmer"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2017.8280949"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2544866"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2018.8489477"},{"key":"ref18","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"Proc. Int. Found. Auto. Agents Multiagent Syst.","author":"Sunehag"},{"key":"ref19","first-page":"1","article-title":"ROMA: Multi-agent reinforcement learning with emergent roles","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref20","article-title":"Multi-agent determinantal Q-learning","author":"Yang","year":"2020","journal-title":"arXiv:2006.01482"},{"key":"ref21","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","author":"Wang","year":"2020","journal-title":"arXiv:2008.01062"},{"key":"ref22","article-title":"Q-value path decomposition for deep multiagent reinforcement learning","author":"Yang","year":"2020","journal-title":"arXiv:2002.03950"},{"key":"ref23","first-page":"5887","article-title":"QTRAN: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Son"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3004893"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6221"},{"key":"ref26","first-page":"1","article-title":"Action semantics network: Considering the effects of actions in multiagent systems","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3356464.3357707"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3041469"},{"key":"ref31","first-page":"2576","article-title":"Grid-wise control for multi-agent reinforcement learning in video game AI","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Han"},{"key":"ref32","article-title":"Multiagent bidirectionally-coordinated nets: Emergence of human-level coordination in learning to play StarCraft combat games","author":"Peng","year":"2017","journal-title":"arXiv:1703.10069"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2832025"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2996209"},{"key":"ref35","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref36","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lillicrap"},{"key":"ref37","first-page":"1","article-title":"RODE: Learning roles to decompose multi-agent tasks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref38","article-title":"Qatten: A general framework for cooperative multiagent reinforcement learning","author":"Yang","year":"2020","journal-title":"arXiv:2002.03939"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref40","first-page":"1","article-title":"Fast and accurate deep network learning by exponential linear units","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Clevert"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref42","first-page":"2186","article-title":"The StarCraft multi-agent challenge","volume-title":"Proc. 18th Int. Conf. Auto. Agents MultiAgent Syst.","author":"Samvelyan"},{"key":"ref43","article-title":"Comparative evaluation of multi-agent deep reinforcement learning algorithms","author":"Papoudakis","year":"2020","journal-title":"arXiv:2006.07869"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10091960\/09525046.pdf?arnumber=9525046","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T23:41:28Z","timestamp":1705016488000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9525046\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4]]},"references-count":43,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3105869","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4]]}}}