{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:51:11Z","timestamp":1767340271731,"version":"3.28.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T00:00:00Z","timestamp":1725408000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T00:00:00Z","timestamp":1725408000000},"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":[[2024,9,4]]},"DOI":"10.1109\/mfi62651.2024.10705775","type":"proceedings-article","created":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T17:45:44Z","timestamp":1728495944000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Deep Reinforcement Learning Method for Control of Mixed Autonomy Traffic Systems"],"prefix":"10.1109","author":[{"given":"Xingyu","family":"Liu","sequence":"first","affiliation":[{"name":"University of Sheffield,Department of Automatic Control and Systems Engineering,Sheffield,United Kingdom,S1 3JD"}]},{"given":"Esa","family":"Apriaskar","sequence":"additional","affiliation":[{"name":"Universitas Negeri Semarang,Faculty of Engineering,Department of Electrical Engineering,Semarang,Indonesia,50229"}]},{"given":"Lyudmila","family":"Mihaylova","sequence":"additional","affiliation":[{"name":"University of Sheffield,Department of Automatic Control and Systems Engineering,Sheffield,United Kingdom,S1 3JD"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569938"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/su131911052"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103101"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2018.02.005"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995897"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2966506"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3168621"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3087314"},{"key":"ref10","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2015.01.063"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2016.2605318"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3166\/ejc.13.297-319"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2016.04.117"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2017.08.017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.tra.2015.03.015"},{"key":"ref17","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"Sutton","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"Actor-critic algorithms","volume":"12","author":"Konda","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref19","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proceedings of the International conference on machine learning","author":"Schulman","year":"2015"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2016.7508798"},{"key":"ref21","article-title":"Using a deep reinforcement learning agent for traffic signal control","author":"Genders","year":"2016","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3063463"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3169907"},{"key":"ref24","first-page":"399","article-title":"Benchmarks for reinforcement learning in mixed-autonomy traffic","volume-title":"Proceedings of The 2nd Conference on Robot Learning","author":"Vinitsky","year":"2018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/VNC48660.2019.9062809"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC57777.2023.10421828"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1287\/opre.7.1.86"},{"journal-title":"Deep Reinforcement learning for real autonomous mobile robot navigation in indoor environments","year":"2020","author":"Surmann","key":"ref28"},{"key":"ref29","article-title":"Implementation matters in deep policy gradients: A case study on PPO and TRPO","author":"Engstrom","year":"2020","journal-title":"arXiv preprint"}],"event":{"name":"2024 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI)","start":{"date-parts":[[2024,9,4]]},"location":"Pilsen, Czech Republic","end":{"date-parts":[[2024,9,6]]}},"container-title":["2024 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10705756\/10705757\/10705775.pdf?arnumber=10705775","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,10]],"date-time":"2024-10-10T15:13:15Z","timestamp":1728573195000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10705775\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,4]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/mfi62651.2024.10705775","relation":{},"subject":[],"published":{"date-parts":[[2024,9,4]]}}}