{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T17:38:53Z","timestamp":1789234733602,"version":"build-2803163510"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1109\/tits.2023.3316285","type":"journal-article","created":{"date-parts":[[2023,9,27]],"date-time":"2023-09-27T17:43:13Z","timestamp":1695836593000},"page":"1384-1393","source":"Crossref","is-referenced-by-count":13,"title":["Imagination-Augmented Reinforcement Learning Framework for Variable Speed Limit Control"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0142-9290","authenticated-orcid":false,"given":"Duo","family":"Li","sequence":"first","affiliation":[{"name":"Department of Engineering, University of Cambridge, Cambridge, U.K"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joan","family":"Lasenby","sequence":"additional","affiliation":[{"name":"Department of Engineering, University of Cambridge, Cambridge, U.K"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Measuring road congestion","author":"Christidis","year":"2012"},{"key":"ref2","volume-title":"Quality of Transport: Eb82.2 Directorate-General for Communication","author":"Agency","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2002.806803"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.7307\/ptt.v28i5.2033"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2007.908562"},{"key":"ref6","article-title":"Variable Speed Limit (VSL)-best management practice","author":"Elefteriadou","year":"2012"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3141\/2470-09"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1002\/atr.1320"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2010.5624974"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2004.08.001"},{"issue":"8","key":"ref11","first-page":"466","article-title":"METANET: A macroscopic simulation program for motorway networks","volume":"31","author":"Messmer","year":"1990","journal-title":"Traffic Eng. Control"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3160374"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2017.02.009"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2014.05.016"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1139\/cjce-2012-0101"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2019.2959344"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-007-9079-x"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2014.01.014"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2016.01.001"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.17159\/2309-8775\/2019\/v61n3a2"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2687620"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MED.2018.8442986"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569615"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCKE48569.2019.8965184"},{"key":"ref25","first-page":"5690","article-title":"Imagination-augmented agents for deep reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Racani\u00e8re"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.326"},{"key":"ref27","article-title":"Imagination-augmented deep reinforcement learning for robotic applications","author":"Thabet","year":"2022"},{"issue":"3","key":"ref28","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"Watkins","year":"1992","journal-title":"Mach. Learn."},{"key":"ref29","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref30","article-title":"Flow: A modular learning framework for mixed autonomy traffic","author":"Wu","year":"2017","journal-title":"arXiv:1710.05465"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102649"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313077"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref34","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2990598"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103900"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294639"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/3118.003.0018"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2904619"},{"key":"ref40","article-title":"Dream to control: Learning behaviors by latent imagination","author":"Hafner","year":"2019","journal-title":"arXiv:1912.01603"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00110"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636550"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.75"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63007-2_30"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3390\/app10144917"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1062"},{"key":"ref47","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref48","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutton"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015015"},{"key":"ref50","first-page":"131","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":"10.3141\/1876-01"},{"issue":"2","key":"ref52","first-page":"26","article-title":"Lecture 6.5-RMSPROP: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"Tieleman","year":"2012","journal-title":"COURSERA, Neural Netw. Mach. Learn."},{"key":"ref53","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"arXiv:1706.03762"},{"key":"ref54","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref55","article-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2018","journal-title":"arXiv:1812.05905"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6979\/10419116\/10265300.pdf?arnumber=10265300","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,6]],"date-time":"2024-02-06T20:33:07Z","timestamp":1707251587000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10265300\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":55,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tits.2023.3316285","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2]]}}}