{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T15:22:21Z","timestamp":1783783341710,"version":"3.55.0"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst., Man, Cybern. C"],"published-print":{"date-parts":[[2012,11]]},"DOI":"10.1109\/tsmcc.2012.2218596","type":"journal-article","created":{"date-parts":[[2012,12,21]],"date-time":"2012-12-21T19:04:54Z","timestamp":1356116694000},"page":"1742-1751","source":"Crossref","is-referenced-by-count":133,"title":["Multiagent-Based Reinforcement Learning for Optimal Reactive Power Dispatch"],"prefix":"10.1109","volume":"42","author":[{"given":"Yinliang","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenxin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Frank","family":"Ferrese","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/9780470544785"},{"key":"ref32","author":"werbos","year":"1994","journal-title":"The Roots of Backpropagation"},{"key":"ref31","first-page":"25","article-title":"Advanced forecasting methods for global crisis warning and models of intelligence","volume":"22","author":"werbos","year":"1977","journal-title":"General Systems Yearbook"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/72.623201"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2002.1000146"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIA.2003.809438"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2003.816054"},{"key":"ref10","first-page":"535","article-title":"An algorithm for distributed reinforcement learning in cooperative multi-agent systems","author":"lauer","year":"2000","journal-title":"Proc Int Conf Machine Learning"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1329125.1329368"},{"key":"ref12","first-page":"656","article-title":"Q-decomposition for reinforcement learning agents","author":"russell","year":"2003","journal-title":"Proc Int Conf Machine Learning"},{"key":"ref13","article-title":"Coordination of independent learners in cooperative Markov games","author":"matignon","year":"2009"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2007.4399095"},{"key":"ref15","first-page":"4388","article-title":"Fast information sharing in networks of autonomous agent","author":"xiao","year":"2008","journal-title":"Proc Amer Control Conf"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2006.887293"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2010.2099675"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2011.2120631"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.1201\/9781439821091","author":"busoniu","year":"2010","journal-title":"Reinforcement Learning and Dynamic Programming Using Function Approximators"},{"key":"ref28","year":"1993","journal-title":"Power systems test case archive"},{"key":"ref4","author":"pham","year":"2000","journal-title":"Intelligent Optimization Techniques Genetic Algorithms Tabu Search Simulated Annealing and Neural Networks"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2004.832154"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2002.807097"},{"key":"ref6","first-page":"233","article-title":"Improved particle swarm optimization algorithm for OPF problems","author":"zhao","year":"2004","journal-title":"Proc IEEE\/PES Power Systems Conf Exposition"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2007.907375"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2005.851969"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.900643"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ISAP.2005.1599265"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/59.141723"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICSET.2008.4746976"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/PICA.1979.720058"},{"key":"ref20","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref22","first-page":"192","article-title":"A distributed reinforcement learning control architecture for multi-link robots—Experimental validation","author":"martin h","year":"2007","journal-title":"Proc Inter Conf on Informatics in Control Autom and Robotics"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2004.831259"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref23","first-page":"217","article-title":"Learning in large cooperative multirobot systems","volume":"16","author":"fernandez","year":"2001","journal-title":"Int J Robot Autom"},{"key":"ref26","author":"watkins","year":"1989","journal-title":"Learning from delayed rewards"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2003.821629"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5326\/6330018\/06392462.pdf?arnumber=6392462","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,11,14]],"date-time":"2017-11-14T07:22:52Z","timestamp":1510644172000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6392462\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,11]]},"references-count":36,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tsmcc.2012.2218596","relation":{},"ISSN":["1094-6977","1558-2442"],"issn-type":[{"value":"1094-6977","type":"print"},{"value":"1558-2442","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,11]]}}}