{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T07:11:10Z","timestamp":1791875470762,"version":"4.3.4"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2013,4,1]],"date-time":"2013-04-01T00:00:00Z","timestamp":1364774400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Signal Process."],"published-print":{"date-parts":[[2013,4]]},"DOI":"10.1109\/tsp.2013.2241057","type":"journal-article","created":{"date-parts":[[2013,1,18]],"date-time":"2013-01-18T14:05:13Z","timestamp":1358517913000},"page":"1848-1862","source":"Crossref","is-referenced-by-count":147,"title":["${{\\cal Q} {\\cal D}}$-Learning: A Collaborative Distributed Strategy for Multi-Agent Reinforcement Learning Through ${\\rm Consensus} + {\\rm Innovations}$"],"prefix":"10.1109","volume":"61","author":[{"given":"Soummya","family":"Kar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jos\u00e9 M. F.","family":"Moura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"H. Vincent","family":"Poor","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1137\/080726380"},{"key":"ref38","first-page":"1088","article-title":"Generalized consensus algorithms in networked systems with erasure links","author":"rabbat","year":"2005","journal-title":"Proc 6th IEEE Workshop on Signal Process Adv Wireless Commun (SPAWC)"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2009.2031203"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2008.2007111"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2006.887293"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2004.834113"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.2009515"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2010.2055862"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2011.2146776"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1986.1104412"},{"key":"ref10","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":"ref40","author":"bertsekas","year":"1976","journal-title":"Dynamic Programming and Stochastic Control"},{"key":"ref11","first-page":"1021","article-title":"Rational and convergent learning in stochastic games","author":"bowling","year":"2001","journal-title":"Proc 17th Int Joint Conf Artif Intell"},{"key":"ref12","first-page":"746","article-title":"The dynamics of reinforcement learning in cooperative multiagent systems","author":"claus","year":"1998","journal-title":"Proc 15th Int Conf Artif Intell"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/S1389-0417(01)00015-8"},{"key":"ref14","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":"ref15","first-page":"227","article-title":"Coordinated reinforcement learning","author":"guestrin","year":"2002","journal-title":"Proc 19th Int Conf Mach Learn"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2004.08.003"},{"key":"ref17","article-title":"Using the max-plus algorithm for multiagent decision making in coordination graphs","author":"kok","year":"2005","journal-title":"Robot Soccer World Cup IX (RoboCup 2005)"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1613\/jair.1024","article-title":"The communicative multiagent team decision problem: Analyzing teamwork theories and models","volume":"16","author":"pynadath","year":"2002","journal-title":"J Artif Intell Res"},{"key":"ref19","first-page":"326","article-title":"Reinforcement learning of coordination in cooperative multi-agent systems","author":"kapetanakis","year":"2002","journal-title":"Proc 18th Nat Conf Artif Intell and 14th Conf Innov Appl Artif Intell"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2010.2052531"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993306"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/Allerton.2011.6120162"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022676722315"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/37.126844"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2003.812781"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.6.1185"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(94)00011-O"},{"key":"ref2","first-page":"242","article-title":"CMUnited: A team of robotic soccer agents collaborating in an adversarial environment","author":"veloso","year":"1997","journal-title":"Proc 1st Robot World Cup Soccer Games and Conf (RoboCup-97)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2010.2081652"},{"key":"ref9","first-page":"310","article-title":"A generalized reinforcement learning model: Convergence and applications","author":"littman","year":"1996","journal-title":"Proc 13th Int Conf Mach Learn"},{"key":"ref20","author":"shoham","year":"2003","journal-title":"Multi-agent reinforcement learning A critical survey"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2011.05.001"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref42","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-662-02514-7","author":"jacod","year":"1987","journal-title":"Limit Theorems for Stochastic Processes"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2011.2127446"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2009.2036046"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2012.2191450"},{"key":"ref44","first-page":"1","article-title":"Learning rates for <formula formulatype=\"inline\"><tex Notation=\"TeX\">$Q$<\/tex><\/formula>-learning","volume":"5","author":"even-dar","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2008.917383"},{"key":"ref43","first-page":"1064","volume":"10","author":"szepesvari","year":"1998","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1137\/110848396"}],"container-title":["IEEE Transactions on Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/78\/6476733\/06415291.pdf?arnumber=6415291","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,29]],"date-time":"2021-11-29T15:55:57Z","timestamp":1638201357000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6415291\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,4]]},"references-count":44,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tsp.2013.2241057","relation":{},"ISSN":["1053-587X","1941-0476"],"issn-type":[{"value":"1053-587X","type":"print"},{"value":"1941-0476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,4]]}}}