{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T13:36:17Z","timestamp":1777037777768,"version":"3.51.4"},"reference-count":29,"publisher":"Informa UK Limited","issue":"6","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52202493"],"award-info":[{"award-number":["52202493"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["Journal of Control and Decision"],"published-print":{"date-parts":[[2025,11,3]]},"DOI":"10.1080\/23307706.2025.2521782","type":"journal-article","created":{"date-parts":[[2025,7,17]],"date-time":"2025-07-17T15:07:01Z","timestamp":1752764821000},"page":"1043-1051","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":1,"title":["Decision making for highway autonomous driving using hybrid reinforcement learning"],"prefix":"10.1080","volume":"12","author":[{"given":"Zeyu","family":"Yang","sequence":"first","affiliation":[{"name":"Hunan University","place":["Changsha, People's Republic of China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lele","family":"Zhang","sequence":"additional","affiliation":[{"name":"Hunan University","place":["Changsha, People's Republic of China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0346-7883","authenticated-orcid":false,"given":"Yougang","family":"Bian","sequence":"additional","affiliation":[{"name":"Hunan University","place":["Changsha, People's Republic of China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manjiang","family":"Hu","sequence":"additional","affiliation":[{"name":"Hunan University","place":["Changsha, People's Republic of China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"301","published-online":{"date-parts":[[2025,7,17]]},"reference":[{"key":"e_1_3_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3285440"},{"key":"e_1_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.3390\/en16083490"},{"key":"e_1_3_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/IV47402.2020.9304744"},{"key":"e_1_3_2_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103656"},{"key":"e_1_3_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3069497"},{"key":"e_1_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3285442"},{"key":"e_1_3_2_8_1","unstructured":"Cheng C.-A. Yan X. Wagener N. & Boots B (2018). Fast policy learning through imitation and reinforcement. Preprint. arXiv:1805.10413."},{"key":"e_1_3_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3102432"},{"key":"e_1_3_2_10_1","unstructured":"Gandhi M. Kundu A. & Bhatnagar S (2020). A reinforcement learning approach to hybrid control design. Preprint. arXiv:2009.00821."},{"key":"e_1_3_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3130054"},{"key":"e_1_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV"},{"key":"e_1_3_2_13_1","unstructured":"Hu Y. Wang R. Li L. E. & Gao Y (2023). For pre-trained vision models in motor control not all policy learning methods are created equal. In International Conference on Machine Learning (pp. 13628\u201313651). PMLR."},{"key":"e_1_3_2_14_1","doi-asserted-by":"publisher","DOI":"10.3141\/1999-10"},{"key":"e_1_3_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3631969"},{"key":"e_1_3_2_16_1","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/10187.001.0001"},{"key":"e_1_3_2_17_1","unstructured":"Leurent E (2018). An environment for autonomous driving decision-making. https:\/\/github.com\/eleurent\/highway-env."},{"key":"e_1_3_2_18_1","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.2200128"},{"key":"e_1_3_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.6979"},{"key":"e_1_3_2_20_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"e_1_3_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2019.8914621"},{"key":"e_1_3_2_22_1","doi-asserted-by":"publisher","DOI":"10.3390\/s21237829"},{"key":"e_1_3_2_23_1","unstructured":"Sharifi I. Yildirim M. & Fallah S (2023). Towards safe autonomous driving policies using a neuro-symbolic deep reinforcement learning approach. Preprint. arXiv:2307.01316."},{"key":"e_1_3_2_24_1","doi-asserted-by":"publisher","DOI":"10.1049\/itr2.v14.6"},{"key":"e_1_3_2_25_1","doi-asserted-by":"crossref","unstructured":"Tasrin T. Nahian M. S. A. Perera H. & Harrison B (2021). Influencing reinforcement learning through natural language guidance. Preprint. arXiv:2104.01506.","DOI":"10.32473\/flairs.v34i1.128472"},{"key":"e_1_3_2_26_1","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"e_1_3_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2025.3535159"},{"key":"e_1_3_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3150343"},{"key":"e_1_3_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3268500"},{"key":"e_1_3_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3266885"}],"container-title":["Journal of Control and Decision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/23307706.2025.2521782","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T11:11:34Z","timestamp":1762945894000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/23307706.2025.2521782"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,17]]},"references-count":29,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,11,3]]}},"alternative-id":["10.1080\/23307706.2025.2521782"],"URL":"https:\/\/doi.org\/10.1080\/23307706.2025.2521782","relation":{},"ISSN":["2330-7706","2330-7714"],"issn-type":[{"value":"2330-7706","type":"print"},{"value":"2330-7714","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,17]]},"assertion":[{"value":"The publishing and review policy for this title is described in its Aims & Scope.","order":1,"name":"peerreview_statement","label":"Peer Review Statement"},{"value":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tjcd20","URL":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tjcd20","order":2,"name":"aims_and_scope_url","label":"Aim & Scope"},{"value":"2024-12-03","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-06-15","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}