{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T19:34:15Z","timestamp":1773776055449,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T00:00:00Z","timestamp":1665187200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T00:00:00Z","timestamp":1665187200000},"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":[[2022,10,8]]},"DOI":"10.1109\/itsc55140.2022.9922531","type":"proceedings-article","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T01:40:13Z","timestamp":1667526013000},"page":"2329-2334","source":"Crossref","is-referenced-by-count":6,"title":["Deep Reinforcement Learning Based Strategy For Optimizing Phase Splits in Traffic Signal Control"],"prefix":"10.1109","author":[{"given":"Huan","family":"Yang","sequence":"first","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University,Singapore,639798"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University,Singapore,639798"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University,Singapore,639798"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guoqiang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University,Singapore,639798"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danwei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University,Singapore,639798"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569241"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/AEECA49918.2020.9213523"},{"key":"ref23","article-title":"Deep reinforcement learning in large discrete action spaces","author":"dulac-arnold","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2019.00314"},{"key":"ref14","article-title":"Urban traffic control in software defined internet of things via a multi-agent deep reinforcement learning approach","author":"yang","year":"2020","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917451"},{"key":"ref11","article-title":"Deep deterministic policy gradient for urban traffic light control","author":"casas","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref22","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref10","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2017.09.020"},{"key":"ref2","article-title":"Deep reinforcement learning for intelligent transportation systems: A survey","author":"haydari","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2014.6958095"},{"key":"ref17","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.29007\/zrzd"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s42421-020-00029-6"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106708"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref7","article-title":"A survey on traffic signal control methods","author":"wei","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref9","article-title":"Using reinforcement learning with partial vehicle detection for intelligent traffic signal control","author":"zhang","year":"2020","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1080\/15472450.2013.810991"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3068287"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2003.819610"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MEDO.2016.7746553"}],"event":{"name":"2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)","location":"Macau, China","start":{"date-parts":[[2022,10,8]]},"end":{"date-parts":[[2022,10,12]]}},"container-title":["2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9921415\/9921739\/09922531.pdf?arnumber=9922531","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,27]],"date-time":"2023-02-27T23:04:07Z","timestamp":1677539047000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9922531\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,8]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/itsc55140.2022.9922531","relation":{},"subject":[],"published":{"date-parts":[[2022,10,8]]}}}