{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T00:11:53Z","timestamp":1775866313797,"version":"3.50.1"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"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":[[2020,8]]},"DOI":"10.1109\/case48305.2020.9216899","type":"proceedings-article","created":{"date-parts":[[2020,10,8]],"date-time":"2020-10-08T16:01:51Z","timestamp":1602172911000},"page":"652-658","source":"Crossref","is-referenced-by-count":19,"title":["Fairness Control of Traffic Light via Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Chenghao","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoteng","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Xia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qianchuan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2016.7508798"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/248156.248175"},{"key":"ref12","article-title":"On the scalability of fair queueing","author":"kortebi","year":"2004","journal-title":"ACM HotNets-III"},{"key":"ref13","article-title":"Recent development and applications of sumo-simulation of urban mobility","volume":"5","author":"krajzewicz","year":"2012","journal-title":"International Journal on Advances in Systems and Measurements"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.64.056132"},{"key":"ref15","first-page":"412","article-title":"Reinforcement learning with function approximation for traffic signal control","volume":"12","author":"prashanth","year":"2010","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357900"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2017.0153"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v28i1.8886","article-title":"Decentralized multi-agent reinforcement learning in average-reward dynamic dcops","author":"nguyen","year":"2014","journal-title":"Twenty-Eighth AAAI Conference on Artificial Intelligence"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2016.06.018"},{"key":"ref4","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"Computer Science"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CCNC.2007.44"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref8","article-title":"Deep reinforcement learning for traffic light control in vehicular networks","author":"liang","year":"2018","journal-title":"arXiv preprint arXiv 1803 11115"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1126\/science.aao1733"},{"key":"ref2","first-page":"29","article-title":"Self-organizing traffic lights","volume":"16","author":"gershenson","year":"2005","journal-title":"Complex Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S0947-3580(98)70119-0"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220096"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2017.09.020"},{"key":"ref22","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Computer Science"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.04.008"},{"key":"ref23","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"}],"event":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","location":"Hong Kong, Hong Kong","start":{"date-parts":[[2020,8,20]]},"end":{"date-parts":[[2020,8,21]]}},"container-title":["2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9210430\/9216730\/09216899.pdf?arnumber=9216899","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,22]],"date-time":"2022-11-22T12:59:02Z","timestamp":1669121942000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9216899\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/case48305.2020.9216899","relation":{},"subject":[],"published":{"date-parts":[[2020,8]]}}}