{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T17:13:21Z","timestamp":1787937201544,"version":"build-2784847793"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100015956","name":"Key Research and Development Program of Guangdong Province","doi-asserted-by":"publisher","award":["2020B0909050003"],"award-info":[{"award-number":["2020B0909050003"]}],"id":[{"id":"10.13039\/501100015956","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100015805","name":"Shenzhen Municipal Science and Technology Innovation Committee","doi-asserted-by":"publisher","award":["CJGJZD20200617102801005"],"award-info":[{"award-number":["CJGJZD20200617102801005"]}],"id":[{"id":"10.13039\/501100015805","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Intell. Transport. Syst. Mag."],"published-print":{"date-parts":[[2023,1]]},"DOI":"10.1109\/mits.2022.3144797","type":"journal-article","created":{"date-parts":[[2022,2,14]],"date-time":"2022-02-14T22:04:07Z","timestamp":1644876247000},"page":"160-180","source":"Crossref","is-referenced-by-count":55,"title":["A Comparison of Deep Reinforcement Learning Models for Isolated Traffic Signal Control"],"prefix":"10.1109","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7896-4809","authenticated-orcid":false,"given":"Feng","family":"Mao","sequence":"first","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1523-1114","authenticated-orcid":false,"given":"Zhiheng","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9428-1960","authenticated-orcid":false,"given":"Li","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1-sidebar2","article-title":"What matters for on-policy deep actor-critic methods? A large-scale study","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Andrychowicz","year":"2020"},{"key":"ref1","volume-title":"Traffic jams cost us $87 billion in lost productivity in 2018, and Boston and DC have the nations worst","year":"2019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2904742"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2017.2709779"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2973736"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2016.7508798"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220096"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CASE48305.2020.9216899"},{"key":"ref8","article-title":"AttendLight: Universal attention-based reinforcement learning model for traffic signal control","author":"Oroojlooy","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2901791"},{"key":"ref10","article-title":"Multi-agent reinforcement learning for networked system control","author":"Chu","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3015811"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2020.3033782"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357902"},{"key":"ref14","article-title":"A survey on traffic signal control methods","author":"Wei","year":"2019"},{"key":"ref15","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref18","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn., PMLR","author":"Bellemare","year":"2017"},{"key":"ref19","first-page":"1096","article-title":"Implicit quantile networks for distributional reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Dabney","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5744"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330949"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5467"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357900"},{"key":"ref25","author":"Zheng","year":"2019","journal-title":"Diagnosing reinforcement learning for traffic signal control"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330988"},{"key":"ref28","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Mnih","year":"2016"},{"key":"ref29","article-title":"An efficient deep reinforcement learning model for urban traffic control","author":"Lin","year":"2018"},{"key":"ref30","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Haarnoja","year":"2018"},{"key":"ref31","article-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2018"},{"key":"ref32","article-title":"Soft actor-critic for discrete action settings","author":"Christodoulou","year":"2019"},{"key":"ref33","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Schulman","year":"2015"},{"key":"ref34","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref35","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Silver","year":"2014"},{"key":"ref36","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Fujimoto","year":"2018"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/0191-2615(94)90002-7"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2009.0070"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569301"},{"key":"ref40","article-title":"Deep deterministic policy gradient for urban traffic light control","author":"Casas","year":"2017"},{"key":"ref41","article-title":"Coordinated deep reinforcement learners for traffic light control","volume-title":"Proc. 2016 Learn., Inference Control Multi-Agent Syst. (NIPS)","author":"Van der Pol"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3447556.3447565"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2017.09.020"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2017.0153"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2013.2255286"},{"key":"ref46","author":"Mnih","year":"2013","journal-title":"Playing Atari with deep reinforcement learning"},{"key":"ref47","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutton","year":"2000"},{"key":"ref48","first-page":"1008","article-title":"Actor-critic algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Konda","year":"2000"},{"key":"ref49","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Haarnoja","year":"2017"},{"issue":"3","key":"ref50","first-page":"128","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":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2907618"},{"key":"ref52","article-title":"Dont decay the learning rate, increase the batch size","author":"Smith","year":"2017"},{"key":"ref53","volume-title":"The nuts and bolts of deep rl research","author":"Schulman","year":"2016"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.2307\/3006800"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-6243-9_2"}],"container-title":["IEEE Intelligent Transportation Systems Magazine"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5117645\/10015073\/09712430.pdf?arnumber=9712430","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T22:55:43Z","timestamp":1705532143000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9712430\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1]]},"references-count":56,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/mits.2022.3144797","relation":{},"ISSN":["1939-1390","1941-1197"],"issn-type":[{"value":"1939-1390","type":"print"},{"value":"1941-1197","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1]]}}}