{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T20:06:50Z","timestamp":1793131610561,"version":"4.5.0"},"reference-count":183,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Function","doi-asserted-by":"publisher","award":["ICER 1830036"],"award-info":[{"award-number":["ICER 1830036"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1109\/tnnls.2021.3106777","type":"journal-article","created":{"date-parts":[[2021,9,2]],"date-time":"2021-09-02T19:58:22Z","timestamp":1630612702000},"page":"2170-2190","source":"Crossref","is-referenced-by-count":97,"title":["Synergistic Integration Between Machine Learning and Agent-Based Modeling: A Multidisciplinary Review"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6427-3946","authenticated-orcid":false,"given":"Wei","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Lehigh University, Bethlehem, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2862-0482","authenticated-orcid":false,"given":"Andrea","family":"Valencia","sequence":"additional","affiliation":[{"name":"Department of Civil, Environmental, and Construction Engineering, University of Central Florida, Orlando, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7162-7017","authenticated-orcid":false,"given":"Ni-Bin","family":"Chang","sequence":"additional","affiliation":[{"name":"Department of Civil, Environmental, and Construction Engineering, University of Central Florida, Orlando, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1257\/aer.p20151023"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.2711216"},{"key":"ref59","first-page":"692","article-title":"Traffic prediction for agent route planning","author":"wagner","year":"2008","journal-title":"Proc Int Conf Comput Sci (ICCS)"},{"key":"ref58","author":"hastie","year":"2009","journal-title":"The Elements of Statistical Learning Data Mining Inference and Prediction"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2016.2531656"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2011.01.045"},{"key":"ref55","first-page":"1","article-title":"Teaching agent-based modelling and Machine Learning in an integrated way","author":"augustijn","year":"2019","journal-title":"Proc 15th Geocomput Adventures Geocomput"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2009.0096"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1147\/rd.33.0210"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1080\/13658816.2010.495076"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1016\/j.matcom.2016.05.008"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2019.02.006"},{"key":"ref178","author":"weng","year":"2019","journal-title":"Meta Reinforcement Learning"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2010.5596363"},{"key":"ref175","article-title":"Neural policy gradient methods: Global optimality and rates of convergence","author":"wang","year":"2019","journal-title":"arXiv 1909 01150"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-36668-3_23"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2018.00127"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974682"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1007\/978-90-481-8927-4_9"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1177\/0049124113506405"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbankfin.2017.08.008"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.ssci.2018.11.028"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2019.1911837"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2010.02.001"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1038\/460685a"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18564\/jasss.3135"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3390\/su9040521"},{"key":"ref179","article-title":"RL2: Fast reinforcement learning via slow reinforcement learning","author":"duan","year":"2016","journal-title":"arXiv 1611 02779"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.jedc.2014.11.014"},{"key":"ref49","first-page":"365","article-title":"Artificial adaptive agents in economic theory","volume":"81","author":"holland","year":"1991","journal-title":"Amer Econ Rev"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WSC.2008.4736060"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1177\/0002764219859639"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2014.00668"},{"key":"ref181","author":"molnar","year":"2020","journal-title":"Interpretable Machine Learning"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9671.2011.01261.x"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-007-9080-5"},{"key":"ref3","author":"shalizi","year":"2021","journal-title":"Top-Down Design"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3389\/fevo.2018.00237"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1515\/9781400822300"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ICTC.2018.8539377"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-68447-8"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(12)60821-6"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-010-9158-x"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1006\/jmps.1997.1205"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1002\/wsbm.45"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1016\/j.jtbi.2004.10.019","article-title":"Simulating the impact of a molecular ‘decision-process’ on cellular phenotype and multicellular patterns in brain tumors","volume":"233","author":"athale","year":"2005","journal-title":"J Theor Biol"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TSTE.2013.2293148"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2011.2174666"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1080\/09528130903065497"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1080\/17517570701275390"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s10614-009-9171-9"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1016\/j.compenvurbsys.2009.10.001"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1080\/17474230701201349"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijepes.2006.03.002"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1080\/13658810410001713399"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.3233\/MGS-130207"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.amepre.2010.10.033"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2015.12.017"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1016\/j.jedc.2018.03.011"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1016\/j.quascirev.2019.105867"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-020-09480-9"},{"key":"ref154","first-page":"1146","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","author":"foerster","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref151","first-page":"962","article-title":"A deep Bayesian policy reuse approach against non-stationary agents","author":"zheng","year":"2018","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/88"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2011.06.045"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/S0304-3800(96)00010-5"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1139\/f95-241"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-58069-7_38"},{"key":"ref25","article-title":"An agent-based model of interdisciplinary interactions in science","author":"raimbault","year":"2020","journal-title":"arXiv 2006 16399"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1139\/x93-249"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecolmodel.2015.10.014"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1006\/tpbi.1993.1005"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1006869"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/S0304-3800(98)00066-0"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1016\/j.simpat.2019.101940"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.soc.28.110601.141117"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1126\/science.1116681"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.082080899"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1007\/s12524-019-01003-8"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-015-1874-3"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1016\/j.agwat.2016.08.018"},{"key":"ref165","first-page":"214","article-title":"Integrating macro and micro scale approaches in the agent-based modeling of residential dynamics","volume":"68","author":"saeedi","year":"2018","journal-title":"Int J Appl Earth Observ Geoinf"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecolmodel.2019.01.019"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.22581\/muet1982.1804.01"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2019.101011"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1007\/s10816-017-9355-x"},{"key":"ref13","first-page":"571","article-title":"Overview of machine learning and data-driven methods in agent-based modeling of energy markets","author":"prasanna","year":"2019","journal-title":"Proc INFORMATIK"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-55889-9_11"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1949.10483310"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219993"},{"key":"ref14","first-page":"125","article-title":"The beginning of the Monte Carlo method","volume":"15","author":"metropolis","year":"1987","journal-title":"Los Alamos Sci"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1016\/S1389-0417(01)00015-8"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1504\/IJCEE.2019.100558"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/ISGTEurope.2019.8905520"},{"key":"ref96","first-page":"1234","article-title":"Multi-agent based modelling of an endogenous-money economy","volume":"34","author":"blecic","year":"2015","journal-title":"Inform Comput"},{"key":"ref127","article-title":"A distributed reinforcement learning solution with knowledge transfer capability for a bike rebalancing problem","author":"xiao","year":"2018","journal-title":"arXiv 1810 04058"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11192-011-0468-9"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.3846\/16484142.2014.953997"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2014.2357079"},{"key":"ref10","first-page":"1","article-title":"Machine learning meets agent-based modeling: When not to go to a bar","author":"rand","year":"2006","journal-title":"Proc Conf Social Agents Results Prospects"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecolmodel.2017.02.013"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/ISGTEurope.2019.8905628"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/WSC.2005.1574234"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecolmodel.2006.04.023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-8748-8"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.2307\/2258570"},{"key":"ref93","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1016\/j.cities.2018.10.008"},{"key":"ref134","first-page":"4897","article-title":"Monte-Carlo tree search by best arm identification","volume":"2017","author":"kaufmann","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2018.03.164"},{"key":"ref131","article-title":"Feature-based Q-learning for two-player stochastic games","author":"jia","year":"2019","journal-title":"arXiv 1906 00423"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/IFCSTA.2009.47"},{"key":"ref132","article-title":"Dynamic programming for extensive-form games with imperfect information","author":"buter","year":"2012"},{"key":"ref130","first-page":"8665","article-title":"Finite-sample analysis for sarsa with linear function approximation","author":"zou","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.31737\/2221-2264-2018-39-3-3"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.2298\/FIL1615101L"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1179\/1749631414Y.0000000041"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1145\/1516512.1516516"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/WSC.2017.8247872"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1016\/S0165-7836(98)00134-9"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM38437.2019.9013999"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1086\/684197"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.18564\/jasss.3733"},{"key":"ref136","article-title":"Starcraft II: A new challenge for reinforcement learning","author":"vinyals","year":"2017","journal-title":"arXiv 1708 04782"},{"key":"ref82","first-page":"332","article-title":"The potential of combined machine learning and agent-based models in water resources management","volume":"63","author":"mewes","year":"2019","journal-title":"Hydrologie und Wasserbewirtschaftung"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/TLA.2019.8891956"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1016\/j.jtbi.2019.110080"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.24200\/sci.2018.20789"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1016\/j.techfore.2014.10.010"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1016\/j.epsr.2015.03.003"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1287\/inte.2019.0997"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2016.2631453"},{"key":"ref140","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":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2968937"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2018.12.002"},{"key":"ref79","doi-asserted-by":"crossref","first-page":"1210","DOI":"10.1109\/TSMCA.2008.2001059","article-title":"Predicting interactions between agents in agent-based modeling and simulation of sociotechnical systems","volume":"38","author":"lee","year":"2008","journal-title":"IEEE Trans Syst Man Cybern A Syst Humans"},{"key":"ref108","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":"ref78","doi-asserted-by":"publisher","DOI":"10.1080\/13658816.2020.1748192"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1980.11718"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.39.10.1953"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2017.06.004"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1515\/amcs-2015-0035"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.jtbi.2018.09.019"},{"key":"ref105","first-page":"183","article-title":"Multi-agent reinforcement learning: An overview","author":"bu?oniu","year":"2010","journal-title":"Innovations in Multi-Agent Systems and Applications - 1"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2017.11.003"},{"key":"ref102","first-page":"1","article-title":"My kingdom for a function: Modeling misadventures of the innumerate","volume":"6","author":"agar","year":"2003","journal-title":"J Artif Societies Social Simul"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)UP.1943-5444.0000255"},{"key":"ref103","first-page":"128","article-title":"Local environment analysis and rules inferring procedure in an agent based model-applications in economics","author":"dospinescu","year":"2012","journal-title":"Romanian Journal of Economic Forecasting"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2013.0378"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1093\/0198247044.001.0001"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-016-9326-8"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008819414322"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v28i1.8914"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-005-5137-x"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecocom.2018.08.004"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46331-5_3"},{"key":"ref110","first-page":"1603","article-title":"Reinforcement learning to play an optimal Nash equilibrium in team Markov games","author":"wang","year":"2003","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijresmar.2011.04.002"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2935201"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s10707-019-00347-0"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/78"},{"key":"ref69","first-page":"1","article-title":"A brief introduction to the use of machine learning techniques in the analysis of agent-based models","author":"pereda","year":"2012","journal-title":"SSRN Electron J"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1002\/adc2.27"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.3233\/AIC-2012-0537"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.04.028"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.econmod.2014.12.040"},{"key":"ref116","article-title":"Cooperative and distributed reinforcement learning of drones for field coverage","author":"pham","year":"2018","journal-title":"arXiv 1803 07250"},{"key":"ref66","first-page":"33","article-title":"Improving building energy efficiency with a network of sensing, learning and prediction agents","volume":"1","author":"mamidi","year":"2012","journal-title":"Proc 11th Int Conf Auton Agents Multiagent Syst"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2014.2312392"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2014.04.024"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2017.11.011"},{"key":"ref60","author":"quinlan","year":"2014","journal-title":"Programs for Machine Learning"},{"key":"ref122","article-title":"Autonomous air traffic controller: A deep multi-agent reinforcement learning approach","author":"brittain","year":"2019","journal-title":"arXiv 1905 01303"},{"key":"ref123","first-page":"1","article-title":"Cooperative reinforcement learning algorithm to distributed power system based on multi-agent","author":"gao","year":"2009","journal-title":"Proc 3rd Int Conf Power Electron Syst Appl (PESA)"},{"key":"ref62","article-title":"Automated algorithmic trading: Machine learning and agent-based modelling in complex adaptive financial markets","author":"booth","year":"2016"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2014.6958095"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50023-2"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/ISACV.2015.7105536"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/5962385\/10114428\/9527397-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10114428\/09527397.pdf?arnumber=9527397","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,22]],"date-time":"2023-05-22T17:55:06Z","timestamp":1684778106000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9527397\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5]]},"references-count":183,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3106777","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5]]}}}