{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T03:09:33Z","timestamp":1780456173289,"version":"3.54.1"},"reference-count":78,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Northeastern University Tier 1 Award titled \u201cMulti-Agent Reinforcement Learning Framework for Learning Coordination and Decision-Making"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3275883","type":"journal-article","created":{"date-parts":[[2023,5,12]],"date-time":"2023-05-12T17:45:26Z","timestamp":1683913526000},"page":"47646-47658","source":"Crossref","is-referenced-by-count":36,"title":["Multi-Agent Reinforcement Learning Based on Representational Communication for Large-Scale Traffic Signal Control"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7189-457X","authenticated-orcid":false,"given":"Rohit","family":"Bokade","sequence":"first","affiliation":[{"name":"Department of Mechanical and Industrial Engineering, Northeastern University, Boston, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9353-8456","authenticated-orcid":false,"given":"Xiaoning","family":"Jin","sequence":"additional","affiliation":[{"name":"Department of Mechanical and Industrial Engineering, Northeastern University, Boston, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher","family":"Amato","sequence":"additional","affiliation":[{"name":"Khoury College of Computer Sciences, Northeastern University, Boston, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","first-page":"21","article-title":"Coordinated deep reinforcement learners for traffic light control","volume":"8","author":"van der pol","year":"2016","journal-title":"Proc Learn Inference Control Multi-Agent Syst (NIPS)"},{"key":"ref57","article-title":"The concrete distribution: A continuous relaxation of discrete random variables","author":"maddison","year":"2016","journal-title":"arXiv 1611 00712"},{"key":"ref12","article-title":"Using a deep reinforcement learning agent for traffic signal control","author":"genders","year":"2016","journal-title":"arXiv 1611 01142"},{"key":"ref56","article-title":"Categorical reparameterization with Gumbel–Softmax","author":"jang","year":"2016","journal-title":"arXiv 1611 01144"},{"key":"ref15","article-title":"Deep reinforcement learning for traffic light control in vehicular networks","author":"liang","year":"2018","journal-title":"arXiv 1803 11115"},{"key":"ref59","article-title":"On the pitfalls of measuring emergent communication","author":"lowe","year":"2019","journal-title":"arXiv 1903 05168"},{"key":"ref14","first-page":"2","article-title":"Heterogeneous multi-agent deep reinforcement learning for traffic lights control","author":"calvo","year":"2018","journal-title":"Proc AICS"},{"key":"ref58","first-page":"1","article-title":"Learning disentangled joint continuous and discrete representations","volume":"31","author":"dupont","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref52","first-page":"1","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2011.2161577"},{"key":"ref55","first-page":"7234","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"rashid","year":"2020","journal-title":"J Mach Learn Res"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-87479-9_61"},{"key":"ref54","article-title":"Deep variational information bottleneck","author":"alemi","year":"2016","journal-title":"arXiv 1612 00410"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2955035"},{"key":"ref16","article-title":"An efficient deep reinforcement learning model for urban traffic control","author":"lin","year":"2018","journal-title":"arXiv 1808 01876"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2904742"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2901791"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6211"},{"key":"ref50","article-title":"Graph convolutional reinforcement learning","author":"jiang","year":"2018","journal-title":"arXiv 1810 09202"},{"key":"ref46","article-title":"Learning to schedule communication in multi-agent reinforcement learning","author":"kim","year":"2019","journal-title":"arXiv 1902 01554"},{"key":"ref45","article-title":"Learning nearly decomposable value functions via communication minimization","author":"wang","year":"2019","journal-title":"arXiv 1910 05366"},{"key":"ref48","article-title":"Learning transferable cooperative behavior in multi-agent teams","author":"agarwal","year":"2019","journal-title":"arXiv 1906 01202"},{"key":"ref47","first-page":"964","article-title":"Multi-agent graph-attention communication and teaming","author":"niu","year":"2021","journal-title":"Proc AAMAS"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-019-05864-5"},{"key":"ref41","first-page":"1","article-title":"VAIN: Attentional multi-agent predictive modeling","volume":"30","author":"hoshen","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref44","article-title":"Learning when to communicate at scale in multiagent cooperative and competitive tasks","author":"singh","year":"2018","journal-title":"arXiv 1812 09755"},{"key":"ref43","first-page":"1","article-title":"Efficient communication in multi-agent reinforcement learning via variance based control","volume":"32","author":"zhang","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref49","first-page":"456","article-title":"Learning correlated communication topology in multi-agent reinforcement learning","author":"du","year":"2021","journal-title":"Proc 20th Int Conf Auto Agents MultiAgent Syst"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113885"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/electronics8030292"},{"key":"ref9","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"},{"key":"ref4","article-title":"The new automobility: Lyft, Uber and the future of American cities","author":"schaller","year":"2018"},{"key":"ref3","year":"2016","journal-title":"E-Stats 2014 Measuring the Electronic Economy"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1186\/1476-069X-9-65"},{"key":"ref5","author":"schrank","year":"2009","journal-title":"TTI’s 2012 urban mobility report Powered by INRIX traffic data"},{"key":"ref40","first-page":"1","article-title":"Learning multiagent communication with backpropagation","volume":"29","author":"sukhbaatar","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2021.104165"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3070835"},{"key":"ref78","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1080\/00031305.1954.10482763","article-title":"Some applications of extreme-value methods","volume":"8","author":"gumbel","year":"1954","journal-title":"Amer Statistician"},{"key":"ref37","article-title":"Variationally and intrinsically motivated reinforcement learning for decentralized traffic signal control","author":"zhu","year":"2021","journal-title":"arXiv 2101 00746"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3062072"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206820"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2013.08.014"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3390\/s20154291"},{"key":"ref74","article-title":"Self-organizing traffic lights","author":"gershenson","year":"2004","journal-title":"arXiv nlin\/0411066"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CASE48305.2020.9216981"},{"key":"ref77","article-title":"The StarCraft multi-agent challenge","author":"samvelyan","year":"2019","journal-title":"arXiv 1902 04043"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5467"},{"key":"ref76","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"10793","DOI":"10.1038\/ncomms10793","article-title":"Understanding congested travel in urban areas","volume":"7","author":"\u00e7olak","year":"2016","journal-title":"Nature Commun"},{"key":"ref1","year":"2014","journal-title":"World Urbanization Prospects the 2014 Revision"},{"key":"ref39","first-page":"1","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume":"29","author":"foerster","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1024"},{"key":"ref71","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"sunehag","year":"2017","journal-title":"arXiv 1706 05296"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref73","author":"roess","year":"2004","journal-title":"Traffic Engineering"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-15024-6_4"},{"key":"ref24","article-title":"Networked multi-agent reinforcement learning with emergent communication","author":"gupta","year":"2020","journal-title":"arXiv 2004 02780"},{"key":"ref68","first-page":"1","article-title":"Deep recurrent Q-learning for partially observable MDPS","author":"hausknecht","year":"2015","journal-title":"Proc AAAI Fall Symp Ser"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357900"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3037348"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3008612"},{"key":"ref69","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-28929-8","author":"oliehoek","year":"2016","journal-title":"A Concise Introduction to Decentralized POMDPs"},{"key":"ref20","article-title":"A survey on traffic signal control methods","author":"wei","year":"2019","journal-title":"arXiv 1904 08117"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3015811"},{"key":"ref63","article-title":"Intelligent traffic light control","author":"wiering","year":"2004"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330949"},{"key":"ref66","article-title":"Multi-agent reinforcement learning for networked system control","author":"chu","year":"2020","journal-title":"arXiv 2004 01339"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357902"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2013.2255286"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CCTA41146.2020.9206275"},{"key":"ref27","first-page":"816","article-title":"Feudal multi-agent deep reinforcement learning for traffic signal control","author":"ma","year":"2020","journal-title":"Proc 19th Int Conf Auto Agents Multiagent Syst (AAMAS)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2020.3033782"},{"key":"ref60","first-page":"164","article-title":"Recent development and applications of sumo-simulation of urban mobility","volume":"5","author":"krajzewicz","year":"2012","journal-title":"Int J Adv Syst Meas"},{"key":"ref62","first-page":"1151","article-title":"Multi-agent reinforcement learning for traffic light control","author":"wiering","year":"2000","journal-title":"Proc 17th Int Conf Mach Learn (ICML)"},{"key":"ref61","first-page":"3040","article-title":"Social influence as intrinsic motivation for multi-agent deep reinforcement learning","author":"jaques","year":"2019","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10123921.pdf?arnumber=10123921","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T09:01:04Z","timestamp":1729414864000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10123921\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":78,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3275883","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}