{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T11:02:32Z","timestamp":1763809352501,"version":"3.37.3"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2015,4,1]],"date-time":"2015-04-01T00:00:00Z","timestamp":1427846400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61035003","61175042","61321491","61202212"],"award-info":[{"award-number":["61035003","61175042","61321491","61202212"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"973 Program of Jiangsu, China","award":["BK2011005"],"award-info":[{"award-number":["BK2011005"]}]},{"DOI":"10.13039\/501100004602","name":"Program for New Century Excellent Talents in University","doi-asserted-by":"publisher","award":["NCET-10-0476"],"award-info":[{"award-number":["NCET-10-0476"]}],"id":[{"id":"10.13039\/501100004602","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Program for Research and Innovation of Graduate Students in General Colleges and Universities, Jiangsu","award":["CXLX13_049"],"award-info":[{"award-number":["CXLX13_049"]}]},{"name":"Collaborative Innovation Center of Novel Software Technology and Industrialization"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2015,4]]},"DOI":"10.1109\/tcyb.2014.2332042","type":"journal-article","created":{"date-parts":[[2014,7,2]],"date-time":"2014-07-02T18:35:04Z","timestamp":1404326104000},"page":"647-662","source":"Crossref","is-referenced-by-count":54,"title":["Multiagent Reinforcement Learning With Unshared Value Functions"],"prefix":"10.1109","volume":"45","author":[{"given":"Yujing","family":"Hu","sequence":"first","affiliation":[]},{"given":"Yang","family":"Gao","sequence":"additional","affiliation":[]},{"given":"Bo","family":"An","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"715","article-title":"Learning multi-agent state space representations","author":"de hauwere","year":"2010","journal-title":"Proc Int Conf Autonomous Agents and Multiagent Systems"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0015117"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-006-0143-1"},{"key":"ref32","first-page":"2","article-title":"Performance bounded reinforcement learning in strategic interactions","volume":"4","author":"banerjee","year":"2004","journal-title":"Proc 19th Nat Conf Artif Intell"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.geb.2006.03.015"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(02)00121-2"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1038\/srep03055"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1038\/srep00620"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-013-9222-4"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-006-9643-2"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/0925-2312(94)00027-P"},{"journal-title":"Games Theory and Applications","year":"1984","author":"thomas","key":"ref40"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.920998"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"311","DOI":"10.3233\/AIC-2010-0476","article-title":"Generalized learning automata for multi-agent reinforcement learning","volume":"23","author":"de hauwere","year":"2010","journal-title":"AI Commun"},{"key":"ref13","first-page":"707","article-title":"Quick polytope approximation of all correlated equilibria in stochastic games","author":"macdermed","year":"2011","journal-title":"Proc 25th AAAI Conf Artif Intell"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref15","first-page":"242","article-title":"Multiagent reinforcement learning: Theoretical framework and an algorithm","author":"hu","year":"1998","journal-title":"Proc 15th Int Conf Mach Learn"},{"key":"ref16","first-page":"1039","article-title":"Nash Q-learning for general-sum stochastic games","volume":"4","author":"hu","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref17","first-page":"322","article-title":"Friend-or-foe Q-learning in general-sum games","author":"littman","year":"2001","journal-title":"Proc 18th Int Conf Mach Learn"},{"key":"ref18","first-page":"242","article-title":"Correlated Q-learning","author":"greenwald","year":"2003","journal-title":"Proc 20th Int Conf Mach Learn"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2010.10.009"},{"key":"ref28","first-page":"1571","article-title":"Reinforcement learning to play an optimal nash equilibrium in team Markov games","volume":"15","author":"wang","year":"2002","journal-title":"Adv Neural Inf Process Syst (NIPS)"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1007\/s11276-012-0457-9","article-title":"Directional routing and scheduling for green vehicular delay tolerant networks","volume":"19","author":"yuanyuan","year":"2013","journal-title":"Wireless Netw"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IAT.2003.1241094"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2010.2099654"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"ref6"},{"journal-title":"Paradoxes of Rationality Games Metagames and Political Behavior","year":"1971","author":"howard","key":"ref29"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1109\/JSAC.2012.120118","article-title":"Game dynamics and cost of learning in heterogeneous 4G networks","volume":"30","author":"manzoor","year":"2012","journal-title":"IEEE J Sel Areas Commun"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2003.817354"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/S1389-1286(00)00090-6"},{"key":"ref2","first-page":"1169","article-title":"MAS for manufacturing control: A layered case study","author":"pedersen","year":"2012","journal-title":"Proc Int Conf Autonomous Agents and Multiagent Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref1","first-page":"111","article-title":"Synergy graphs for configuring robot team members","author":"liemhetcharat","year":"2013","journal-title":"Proc Int Conf Auton Agents and Multi Agent Syst"},{"key":"ref20","first-page":"609","article-title":"Agent-mediated multi-step optimization for resource allocation in distributed sensor networks","author":"an","year":"2011","journal-title":"Proc Int Conf Autonomous Agents and Multiagent Systems"},{"key":"ref22","first-page":"746","article-title":"The dynamics of reinforcement learning in cooperative multiagent systems","author":"claus","year":"1998","journal-title":"Proc Nat Conf Artif Intell"},{"key":"ref21","first-page":"551","article-title":"Heuristics for negotiation schedules in multi-plan optimization","author":"an","year":"2008","journal-title":"Proc Int Joint Conf Autonomous Agents and Multiagent Systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2007.02.004"},{"key":"ref23","first-page":"535","article-title":"An algorithm for distributed reinforcement learning in cooperative multi-agent systems","author":"lauer","year":"2000","journal-title":"Proc 17th Int Conf Mach Learn"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/0304-4068(74)90037-8"},{"article-title":"Learning from delayed rewards","year":"1989","author":"watkins","key":"ref25"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/7060779\/06847689.pdf?arnumber=6847689","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:06:40Z","timestamp":1642003600000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/6847689\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,4]]},"references-count":40,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2014.2332042","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"type":"print","value":"2168-2267"},{"type":"electronic","value":"2168-2275"}],"subject":[],"published":{"date-parts":[[2015,4]]}}}