{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T11:15:24Z","timestamp":1762946124077,"version":"3.45.0"},"reference-count":40,"publisher":"Informa UK Limited","issue":"6","funder":[{"DOI":"10.13039\/501100008095","name":"Yanshan University","doi-asserted-by":"publisher","award":["2022BZZD005"],"award-info":[{"award-number":["2022BZZD005"]}],"id":[{"id":"10.13039\/501100008095","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003787","name":"Hebei Natural Science Foundation","doi-asserted-by":"publisher","award":["F2024203083"],"award-info":[{"award-number":["F2024203083"]}],"id":[{"id":"10.13039\/501100003787","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\/23307706.2025.2512920","type":"journal-article","created":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T17:41:59Z","timestamp":1758908519000},"page":"1007-1021","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive double soft actor-critic architecture for intelligent vehicle platooning"],"prefix":"10.1080","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0404-9533","authenticated-orcid":false,"given":"Xiaoyuan","family":"Luo","sequence":"first","affiliation":[{"name":"Yanshan University","place":["Qinhuangdao, People's Republic of China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Gao","sequence":"additional","affiliation":[{"name":"Yanshan University","place":["Qinhuangdao, People's Republic of China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaobao","family":"Li","sequence":"additional","affiliation":[{"name":"Yanshan University","place":["Qinhuangdao, People's Republic of China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiange","family":"Wang","sequence":"additional","affiliation":[{"name":"Yanshan University","place":["Qinhuangdao, People's Republic of China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"301","published-online":{"date-parts":[[2025,9,26]]},"reference":[{"key":"e_1_3_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3285442"},{"key":"e_1_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2024.3404403"},{"key":"e_1_3_2_4_1","unstructured":"Chu T. Chinchali S. & Katti S. (2020). Multi-agent reinforcement learning for networked system control. Preprint arXiv:2004.01339."},{"key":"e_1_3_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.6979"},{"key":"e_1_3_2_6_1","unstructured":"Diederik P. K. (2014). Adam: A method for stochastic optimization. (No Title)."},{"key":"e_1_3_2_7_1","unstructured":"Fujimoto S. Hoof H. & Meger D. (2018). Addressing function approximation error in actor-critic methods. In International Conference on Machine Learning (pp.\u00a01587\u20131596)."},{"key":"e_1_3_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2015.2498841"},{"key":"e_1_3_2_9_1","unstructured":"Haarnoja T. Zhou A. Abbeel P. & Levine S. (2018). Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In International Conference on Machine Learning (pp.\u00a01861\u20131870)."},{"key":"e_1_3_2_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2024.104486"},{"key":"e_1_3_2_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2023.10.005"},{"key":"e_1_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3303408"},{"key":"e_1_3_2_13_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"e_1_3_2_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103744"},{"key":"e_1_3_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CoG47356.2020.9231687"},{"issue":"1","key":"e_1_3_2_16_1","first-page":"1","article-title":"State-of-the-art and technical trends of intelligent and connected vehicles","volume":"8","author":"Keqiang L.","year":"2017","unstructured":"Keqiang, L., Yifan, D., Shengbo, L., & Mingyuan, B. (2017). State-of-the-art and technical trends of intelligent and connected vehicles. Journal of Automotive Safety and Energy, 8(1), 1.","journal-title":"Journal of Automotive Safety and Energy"},{"key":"e_1_3_2_17_1","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2010.0084"},{"key":"e_1_3_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"e_1_3_2_19_1","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2010.0138"},{"key":"e_1_3_2_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2021.03.003"},{"key":"e_1_3_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2016.2541219"},{"key":"e_1_3_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2017.2709781"},{"key":"e_1_3_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/IV47402.2020.9304647"},{"key":"e_1_3_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2016.2578706"},{"key":"e_1_3_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207663"},{"key":"e_1_3_2_26_1","doi-asserted-by":"publisher","DOI":"10.1002\/9780470182963"},{"key":"e_1_3_2_27_1","doi-asserted-by":"publisher","DOI":"10.1287\/educ.2014.0128"},{"key":"e_1_3_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.6979"},{"key":"e_1_3_2_29_1","volume-title":"Markov decision processes: Discrete stochastic dynamic programming","author":"Puterman M. L.","year":"2014","unstructured":"Puterman, M. L. (2014). Markov decision processes: Discrete stochastic dynamic programming. John Wiley & Sons."},{"key":"e_1_3_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIoT.6488907"},{"key":"e_1_3_2_31_1","volume-title":"31st Conference on Neural Information Processing Systems (NIPS 2017)","author":"Rajeswaran A.","year":"2017","unstructured":"Rajeswaran, A., Lowrey, K., Todorov, E. V., & Kakade, S. M.\u00a0(2017). Towards generalization and simplicity in continuous control. In 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA.."},{"key":"e_1_3_2_32_1","unstructured":"Shalev-Shwartz S. Shammah S. & Shashua A. (2016). Safe multi-agent reinforcement learning for autonomous driving. Preprint arXiv:1610.03295."},{"key":"e_1_3_2_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2023.104019"},{"key":"e_1_3_2_34_1","unstructured":"Silver D. Lever G. Heess N. Degris T. Wierstra D. & Riedmiller M. (2014). Deterministic policy gradient algorithms. In International Conference on Machine Learning (pp.\u00a0387\u2013395)."},{"key":"e_1_3_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2005.1469949"},{"key":"e_1_3_2_36_1","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"e_1_3_2_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0001-4575(02)00022-2"},{"key":"e_1_3_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500556"},{"key":"e_1_3_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3116063"},{"key":"e_1_3_2_40_1","doi-asserted-by":"publisher","DOI":"10.3141\/1999-15"},{"key":"e_1_3_2_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102662"}],"container-title":["Journal of Control and Decision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/23307706.2025.2512920","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T11:11:54Z","timestamp":1762945914000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/23307706.2025.2512920"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,26]]},"references-count":40,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,11,3]]}},"alternative-id":["10.1080\/23307706.2025.2512920"],"URL":"https:\/\/doi.org\/10.1080\/23307706.2025.2512920","relation":{},"ISSN":["2330-7706","2330-7714"],"issn-type":[{"type":"print","value":"2330-7706"},{"type":"electronic","value":"2330-7714"}],"subject":[],"published":{"date-parts":[[2025,9,26]]},"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":"2024-12-06","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-26","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}