{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T23:36:51Z","timestamp":1772321811286,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,3,13]],"date-time":"2023-03-13T00:00:00Z","timestamp":1678665600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,3,13]],"date-time":"2023-03-13T00:00:00Z","timestamp":1678665600000},"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":[],"published-print":{"date-parts":[[2023,3,13]]},"DOI":"10.1109\/percomworkshops56833.2023.10150326","type":"proceedings-article","created":{"date-parts":[[2023,6,23]],"date-time":"2023-06-23T11:02:56Z","timestamp":1687518176000},"page":"15-20","source":"Crossref","is-referenced-by-count":4,"title":["A Novel Multi-Agent Deep RL Approach for Traffic Signal Control"],"prefix":"10.1109","author":[{"given":"Wang","family":"Shijie","sequence":"first","affiliation":[{"name":"School of Advanced Technology, Xi’an Jiaotong-Liverpool University,Suzhou,China"}]},{"given":"Wang","family":"Shangbo","sequence":"additional","affiliation":[{"name":"School of Advanced Technology, Xi’an Jiaotong-Liverpool University,Suzhou,China"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Friend-or-foe q-learning in general-sum games","author":"littman","year":"2001","journal-title":"International Conference on Machine Learning"},{"key":"ref12","article-title":"A survey and critique of multiagent deep reinforcement learning","author":"hernandez-leal","year":"2018","journal-title":"Autonomous Agents and Multi-Agent Systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2009.0096"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1155\/2014\/759097"},{"key":"ref11","article-title":"Counterfactual multi-agent policy gradients","author":"foerster","year":"2017","journal-title":"National Conference on Artificial Intelligence"},{"key":"ref10","author":"lowe","year":"2017","journal-title":"Multi-agent actor-critic for mixed cooperative-competitive environments"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2973404"},{"key":"ref1","article-title":"A survey on traffic signal control methods","author":"wei","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CCDC.2019.8832406"},{"key":"ref16","first-page":"21","article-title":"Coordinated deep reinforcement learners for traffic light control","volume":"8","author":"van der pol","year":"2016","journal-title":"Proceedings of Learning Inference and Control of Multi-Agent Systems (at NIPS 2016)"},{"key":"ref19","author":"howard","year":"1960","journal-title":"Dynamic Programming and Markov Processes"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1646\/1\/012077"},{"key":"ref24","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"ArXiv Preprint"},{"key":"ref23","author":"rijken","year":"2015","journal-title":"Deep Light Deep reinforcement learning for signalised traffic control"},{"key":"ref26","first-page":"242","article-title":"Multiagent reinforcement learning: theoretical framework and an algorithm","volume":"98","author":"hu","year":"1998","journal-title":"ICML"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1111\/itor.12039"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"ref22","article-title":"Policy search by dynamic programming","author":"bagnell","year":"2003","journal-title":"Neural Information Processing Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177704593"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220096"},{"key":"ref7","article-title":"On-line q-learning using connectionist systems","author":"rummery","year":"1994","journal-title":"CTIT Technical Reports Series"},{"key":"ref9","article-title":"Multi-agent deep reinforcement learning for large-scale traffic signal control","author":"chu","year":"2019","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"ref4","article-title":"A survey on reinforcement learning models and algorithms for traffic signal control","author":"yau","year":"2017","journal-title":"ACM Computing Surveys"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2020.105713"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref5","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"}],"event":{"name":"2023 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops)","location":"Atlanta, GA, USA","start":{"date-parts":[[2023,3,13]]},"end":{"date-parts":[[2023,3,17]]}},"container-title":["2023 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10149845\/10150216\/10150326.pdf?arnumber=10150326","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,10]],"date-time":"2023-07-10T13:40:52Z","timestamp":1688996452000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10150326\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,13]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/percomworkshops56833.2023.10150326","relation":{},"subject":[],"published":{"date-parts":[[2023,3,13]]}}}