{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T22:22:23Z","timestamp":1770330143198,"version":"3.49.0"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2015,12,1]],"date-time":"2015-12-01T00:00:00Z","timestamp":1448928000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"Foundation of National 863 Plan of China","award":["2012AA111902-2"],"award-info":[{"award-number":["2012AA111902-2"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities of China","doi-asserted-by":"crossref","award":["DUT14RC(3)064"],"award-info":[{"award-number":["DUT14RC(3)064"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Post-Doctoral Science Foundation of China","award":["2014M561229"],"award-info":[{"award-number":["2014M561229"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2015,12]]},"DOI":"10.1109\/tcyb.2014.2387277","type":"journal-article","created":{"date-parts":[[2015,1,13]],"date-time":"2015-01-13T21:45:50Z","timestamp":1421185550000},"page":"2853-2867","source":"Crossref","is-referenced-by-count":45,"title":["Multiagent Learning of Coordination in Loosely Coupled Multiagent Systems"],"prefix":"10.1109","volume":"45","author":[{"given":"Chao","family":"Yu","sequence":"first","affiliation":[]},{"given":"Minjie","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Fenghui","family":"Ren","sequence":"additional","affiliation":[]},{"given":"Guozhen","family":"Tan","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"1440","article-title":"Interaction structure and dimensionality in decentralized problem solving","author":"allen","year":"2008","journal-title":"Proc 23rd AAAI Conf Artif Intell"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1613\/jair.1497","article-title":"Solving transition independent decentralized Markov decision processes","volume":"22","author":"becker","year":"2004","journal-title":"J Artif Intell Res"},{"key":"ref33","first-page":"478","article-title":"Sequential optimality and coordination in multiagent systems","volume":"16","author":"boutilier","year":"1999","journal-title":"Proc Int Joint Conf Artif Intell"},{"key":"ref32","first-page":"195","article-title":"Planning, learning and coordination in multiagent decision processes","author":"boutilier","year":"1996","journal-title":"Proc 6th Conf Theor Aspects Ration Knowl"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/544862.544946"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-007-9026-5"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/860575.860583"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-25832-9_40"},{"key":"ref35","first-page":"525","article-title":"Interaction-driven Markov games for decentralized multiagent planning under uncertainty","volume":"1","author":"spaan","year":"2008","journal-title":"Proc 7th Int Joint Conf Auton Agents Multiagent Syst (AAMS)"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2011.05.001"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1287\/moor.27.4.819.297"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref29","first-page":"19","article-title":"Complexity of decentralized control: Special cases","volume":"22","author":"allen","year":"2009","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-11876-0_14"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref20","first-page":"29","article-title":"Utile coordination: Learning interdependencies among cooperative agents","author":"kok","year":"2005","journal-title":"Proc IEEE Symp Comput Intel Games"},{"key":"ref22","first-page":"83","article-title":"Learning what to observe in multi-agent systems","author":"de hauwere","year":"2009","journal-title":"Proc 20th Belgian-Netherlands Conf Artif Intell"},{"key":"ref21","first-page":"371","article-title":"Distributed value functions","author":"schneider","year":"1999","journal-title":"Proc 16th Int Conf Mach Learn"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015410"},{"key":"ref23","first-page":"715","article-title":"Learning multi-agent state space representations","volume":"1","author":"de hauwere","year":"2010","journal-title":"Proc 9th Int Conf Auton Agents Multiagent Syst"},{"key":"ref26","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1137\/070685610"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2012.2196432"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2332042"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2007.904544"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-005-2631-2"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2007.02.004"},{"key":"ref40","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":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2006.12.006"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2006.12.005"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/11691839_1"},{"key":"ref15","first-page":"469","article-title":"Exploiting factored representations for decentralized execution in multiagent teams","author":"roth","year":"2007","journal-title":"Proc Int Joint Conf Autonomous Agents and Multiagent Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-006-7035-4"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1023\/A:1025696116075"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/375735.376302"},{"key":"ref19","first-page":"227","article-title":"Coordinated reinforcement learning","author":"guestrin","year":"2002","journal-title":"Proc 19th Int Conf Mach Learn"},{"key":"ref4","first-page":"739","article-title":"Self-organization for coordinating decentralized reinforcement learning","volume":"1","author":"zhang","year":"2010","journal-title":"Proc 9th Int Conf Auton Agents Multiagent Syst"},{"key":"ref3","article-title":"Multiagent reinforcement learning for multi-robot systems: A survey","author":"yang","year":"2004"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICAC.2006.1662383"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1613\/jair.1427","article-title":"Decentralized control of cooperative systems: Categorization and complexity analysis","volume":"22","author":"goldman","year":"2004","journal-title":"J Artif Intell Res"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1023\/A:1015504423309"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10723-005-9003-7"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2006.05.012"},{"key":"ref9","first-page":"1396","article-title":"Learned behaviors of multiple autonomous agents in smart grid markets","author":"reddy","year":"2011","journal-title":"Proc Assoc Adv Artif Intell (AAAI)"},{"key":"ref46","article-title":"Planning under uncertainty in complex structured environments","author":"guestrin","year":"2003"},{"key":"ref45","first-page":"65","article-title":"Sparse tabular multiagent Q-learning","author":"kok","year":"2004","journal-title":"Proc Annu Mach Learn Conf Belgium Netherlands"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1177\/0278364908100177"},{"key":"ref47","first-page":"773","article-title":"Learning of coordination: Exploiting sparse interactions in multiagent systems","volume":"2 budapest hungary","author":"melo","year":"2009","journal-title":"Proc 8th Int Conf Auton Agents Multiagent Syst"},{"key":"ref42","first-page":"426","article-title":"Learning to coordinate without sharing information","volume":"1","author":"sen","year":"1994","journal-title":"Proc Nat Conf Artif Intell"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref44","first-page":"2629","article-title":"Hierarchical average reward reinforcement learning","volume":"8","author":"ghavamzadeh","year":"2007","journal-title":"J Mach Learn Res"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.2947"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/7328787\/07008514.pdf?arnumber=7008514","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,26]],"date-time":"2022-04-26T19:21:47Z","timestamp":1651000907000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7008514\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,12]]},"references-count":53,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2014.2387277","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,12]]}}}