{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T14:29:41Z","timestamp":1774621781400,"version":"3.50.1"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation (NSF) CAREER","doi-asserted-by":"publisher","award":["2239566"],"award-info":[{"award-number":["2239566"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004093","name":"Kwanjeong Educational Foundation Ph.D. Scholarship Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004093","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014786","name":"Utah Department of Transportation","doi-asserted-by":"publisher","award":["F-ST99(783)"],"award-info":[{"award-number":["F-ST99(783)"]}],"id":[{"id":"10.13039\/100014786","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tits.2025.3550418","type":"journal-article","created":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T17:42:45Z","timestamp":1745343765000},"page":"7780-7791","source":"Crossref","is-referenced-by-count":2,"title":["Reinforcement Learning for Robust Advisories Under Driving Compliance Errors"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5004-7630","authenticated-orcid":false,"given":"Jeongyun","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Civil and Environmental Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3294-321X","authenticated-orcid":false,"given":"Jung-Hoon","family":"Cho","sequence":"additional","affiliation":[{"name":"Department of Civil and Environmental Engineering and the Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8594-303X","authenticated-orcid":false,"given":"Cathy","family":"Wu","sequence":"additional","affiliation":[{"name":"Laboratory for Information and Decision Systems, Institute for Data, Systems, and Society, and the Department of Civil and Environmental Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2016.07.007"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2021.3125562"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2023.105765"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/10\/3\/033001"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3087314"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/su10041060"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1080\/19427867.2019.1662561"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2018.02.005"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3168621"},{"key":"ref10","first-page":"398","article-title":"Emergent behaviors in mixed-autonomy traffic","volume-title":"Proc. Conf. Robot Learn.","author":"Wu"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9565000"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569615"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569485"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460567"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.7249\/CT463"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564789"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2016.10.014"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2020.3044180"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.sbspro.2013.08.124"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.trd.2018.11.019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3141\/2058-20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/5254.820333"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2015.396"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2023.3338234"},{"key":"ref25","volume-title":"Tracking Skill and Manual Control","year":"1974"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1076\/vesd.40.1.101.15875"},{"key":"ref27","article-title":"Efficient action robust reinforcement learning with probabilistic policy execution uncertainty","author":"Liu","year":"2023","journal-title":"arXiv:2307.07666"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2020.2991948"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2010.2046695"},{"key":"ref30","article-title":"Temporal transfer learning for traffic optimization with coarse-grained advisory autonomy","author":"Cho","year":"2023","journal-title":"arXiv:2312.09436"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10918"},{"key":"ref32","article-title":"Learning to repeat: Fine grained action repetition for deep reinforcement learning","author":"Sharma","year":"2017","journal-title":"arXiv:1702.06054"},{"key":"ref33","first-page":"914","article-title":"TempoRL: Learning when to act","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Biedenkapp"},{"key":"ref34","first-page":"6862","article-title":"Control frequency adaptation via action persistence in batch reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"1","author":"Metelli"},{"key":"ref35","first-page":"3254","article-title":"Reinforcement learning for control with multiple frequencies","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Lee"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1177\/1541931213571433"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1177\/0018720816634226"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.trf.2014.09.005"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1177\/1541931214581434"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2015.02.023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.17077\/drivingassessment.1472"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2018.2845799"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2021.3075455"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1177\/09544070231192139"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2022.11.265"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/SMC53654.2022.9945577"},{"key":"ref47","first-page":"21024","article-title":"Robust deep reinforcement learning against adversarial perturbations on state observations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Zhang"},{"key":"ref48","article-title":"Who is the strongest enemy? Towards optimal and efficient evasion attacks in deep RL","author":"Sun","year":"2021","journal-title":"arXiv:2106.05087"},{"key":"ref49","first-page":"6215","article-title":"Action robust reinforcement learning and applications in continuous control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tessler"},{"key":"ref50","article-title":"Robust temporal difference learning for critical domains","author":"Klima","year":"2019","journal-title":"arXiv:1901.08021"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1050.0216"},{"key":"ref52","first-page":"7193","article-title":"Online robust reinforcement learning with model uncertainty","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Wang"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32430-8_14"},{"key":"ref54","first-page":"7214","article-title":"Non-stationary Markov decision processes, a worst-case approach using model-based reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Lecarpentier"},{"key":"ref55","first-page":"1328","article-title":"Certified adversarial robustness for deep reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"L\u00fctjens"},{"key":"ref56","first-page":"700","article-title":"Domain randomization for simulation-based policy optimization with transferability assessment","volume-title":"Proc. Conf. Robot Learn.","author":"Muratore"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.51.1035"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1287\/opre.7.1.86"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1287\/opre.9.4.545"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6979\/11021249\/10974413-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6979\/11021249\/10974413.pdf?arnumber=10974413","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T17:53:31Z","timestamp":1748973211000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10974413\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":60,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tits.2025.3550418","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}