{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T15:45:44Z","timestamp":1774021544853,"version":"3.50.1"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2020YFB1806403"],"award-info":[{"award-number":["2020YFB1806403"]}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2022B1515120002"],"award-info":[{"award-number":["2022B1515120002"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62201307"],"award-info":[{"award-number":["62201307"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["ZDSYS20210623091808025"],"award-info":[{"award-number":["ZDSYS20210623091808025"]}]},{"name":"Major Key Project of PCL","award":["PCL2024A01"],"award-info":[{"award-number":["PCL2024A01"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Veh. Technol."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/tvt.2024.3388499","type":"journal-article","created":{"date-parts":[[2024,4,15]],"date-time":"2024-04-15T17:30:03Z","timestamp":1713202203000},"page":"12328-12344","source":"Crossref","is-referenced-by-count":13,"title":["Joint Trajectory and Communication Optimization for Heterogeneous Vehicles in Maritime SAR: Multi-Agent Reinforcement Learning"],"prefix":"10.1109","volume":"73","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9844-3671","authenticated-orcid":false,"given":"Chengjia","family":"Lei","sequence":"first","affiliation":[{"name":"Department of Electronics and Information Engineering, Harbin Institute of Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6950-0594","authenticated-orcid":false,"given":"Shaohua","family":"Wu","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Aerospace Communication and Networking Technology, Harbin Institute of Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6525-3920","authenticated-orcid":false,"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8299-9935","authenticated-orcid":false,"given":"Jiayin","family":"Xue","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9272-0475","authenticated-orcid":false,"given":"Qinyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Aerospace Communication and Networking Technology, Harbin Institute of Technology, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Global marine technology trends 2030","author":"Shenoi","year":"2015"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2360368"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.2000076"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3088609"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3000803"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.2974047"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.23919\/JCIN.2019.8916645"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3205127"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2990927"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3181141"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3194927"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3201017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3233087"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IMCEC46724.2019.8984116"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/Ucom59132.2023.10257629"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2020-Fall49728.2020.9348481"},{"key":"ref18","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref19","first-page":"1","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lowe","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3030190"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2022.3160697"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3020400"},{"key":"ref24","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Yu","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3232815"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3232806"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_15"},{"key":"ref28","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Proc. Adv. Int. Conf. Machin. Learn. Syst.","volume":"99","author":"Andrew","year":"1999"},{"key":"ref29","first-page":"7234","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-04105-y"},{"key":"ref31","first-page":"5792","article-title":"Distral: Robust multitask reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst","author":"Teh","year":"2017"},{"key":"ref32","first-page":"1","article-title":"High-dimensional continuous control using generalized advantage estimation","volume-title":"Proc. Adv. Int. Conf. Learn. Representations","author":"Schulman","year":"2016"},{"key":"ref33","first-page":"4287","article-title":"Learning values across many orders of magnitude","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"van Hasselt","year":"2016"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3034628"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2902559"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3166110"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOMWKSHPS54753.2022.9798305"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref41","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref42","article-title":"Is independent learning all you need in the starcraft multi-agent challenge?","author":"Witt","year":"2020"}],"container-title":["IEEE Transactions on Vehicular Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/25\/10683799\/10499870.pdf?arnumber=10499870","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T07:16:55Z","timestamp":1726730215000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10499870\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":42,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tvt.2024.3388499","relation":{},"ISSN":["0018-9545","1939-9359"],"issn-type":[{"value":"0018-9545","type":"print"},{"value":"1939-9359","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}