{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T09:32:30Z","timestamp":1782811950868,"version":"3.54.5"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2014,2,1]],"date-time":"2014-02-01T00:00:00Z","timestamp":1391212800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2014,2,1]],"date-time":"2014-02-01T00:00:00Z","timestamp":1391212800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2014,2,1]],"date-time":"2014-02-01T00:00:00Z","timestamp":1391212800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2014,2]]},"DOI":"10.1109\/tcyb.2013.2253094","type":"journal-article","created":{"date-parts":[[2013,4,15]],"date-time":"2013-04-15T14:42:10Z","timestamp":1366036930000},"page":"252-265","source":"Crossref","is-referenced-by-count":63,"title":["Heuristically-Accelerated Multiagent Reinforcement Learning"],"prefix":"10.1109","volume":"44","author":[{"given":"Reinaldo A. C.","family":"Bianchi","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, Centro Universitário da FEI, São Bernardo do Campo, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Murilo F.","family":"Martins","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Centro Universitário da FEI, São Bernardo do Campo, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carlos H. C.","family":"Ribeiro","sequence":"additional","affiliation":[{"name":"Computer Science Division, Technological Institute of Aeronautics, São José dos Campos, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anna H. R.","family":"Costa","sequence":"additional","affiliation":[{"name":"Escola Politécnica, Universidade of São Paulo, São Paulo, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","author":"spiegel","year":"1998","journal-title":"Statistics"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007562800292"},{"key":"ref33","first-page":"75","article-title":"Improving reinforcement learning by using case based heuristics","author":"bianchi","year":"2009","journal-title":"Proc Int Conf Case-Based Reasoning"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1007\/978-3-540-68847-1_19","article-title":"Heuristic reinforcement learning applied to robocup simulation agents","volume":"lncs 5001","author":"celiberto","year":"2008","journal-title":"Robocup 2007 Robot Soccer World Cup"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/860575.860686"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref37","first-page":"73","article-title":"Robocup: A challenge problem for AI","volume":"18","author":"kitano","year":"1997","journal-title":"AI Mag"},{"key":"ref36","author":"singh","year":"1994","journal-title":"Learning to Solve Markovian Decision Processes"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","article-title":"Reinforcement learning: A survey","volume":"4","author":"kaelbling","year":"1996","journal-title":"J Artif Intell Res"},{"key":"ref34","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":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10732-007-9031-5"},{"key":"ref11","first-page":"169","article-title":"Heuristically accelerated reinforcement learning: Theoretical and experimental results","volume":"242","author":"bianchi","year":"2012","journal-title":"Proc 10th Eur Conf Artificial Intell"},{"key":"ref12","first-page":"690","article-title":"Heuristic selection of actions in multiagent reinforcement learning","author":"bianchi","year":"2007","journal-title":"Proc 20th Int Joint Conf Artif Intell"},{"key":"ref13","first-page":"825","article-title":"Fast concurrent reinforcement learners","author":"banerjee","year":"2001","journal-title":"Proc 17th Int Joint Conf Artif Intell"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/545104.545106"},{"key":"ref15","author":"smith","year":"2003","journal-title":"3D Robot Soccer Simulator"},{"key":"ref16","author":"russell","year":"2009","journal-title":"Artificial Intelligence - A Modern Approach"},{"key":"ref17","author":"watkins","year":"1989","journal-title":"Learning from delayed rewards"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref19","author":"strang","year":"1988","journal-title":"Linear Algebra and its Applications"},{"key":"ref4","first-page":"82","article-title":"Simultaneous abstract and concrete reinforcement learning","author":"matos","year":"2011","journal-title":"Proc 4th Int Symp Abstraction Reformulation and Approximation"},{"key":"ref28","author":"bowling","year":"2000","journal-title":"An analysis of stochastic game theory for multiagent reinforcement learning"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2010.03.007"},{"key":"ref6","first-page":"107","article-title":"Autonomic multi-agent management of power and performance in data centers","author":"das","year":"2008","journal-title":"Proc Int Joint Conf Autonomous Agents and Multiagent Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(02)00121-2"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511794797"},{"key":"ref8","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":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref2","author":"szepesv\ufffdri","year":"1996","journal-title":"Generalized markov decision processes Dynamic-programming and reinforcement-learning algorithms"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/jmlr.2003.4.6.1039"},{"key":"ref1","author":"bertsekas","year":"2007","journal-title":"Dynamic Programming and Optimal Control"},{"key":"ref20","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":"ref22","first-page":"242","article-title":"Correlated Q-learning","author":"greenwald","year":"2003","journal-title":"Proc 20th Int Conf Mach Learn"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44565-X_13"},{"key":"ref24","first-page":"487","author":"tan","year":"1997","journal-title":"Readings in Agents"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-005-2631-2"},{"key":"ref26","author":"yang","year":"2004","journal-title":"Multiagent reinforcement learning for multi-robot systems A survey"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008942012299"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/6710254\/06502216.pdf?arnumber=6502216","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T18:06:23Z","timestamp":1753207583000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/6502216\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,2]]},"references-count":39,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2013.2253094","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,2]]}}}