{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T16:24:34Z","timestamp":1789575874863,"version":"build-2803163510"},"reference-count":92,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["IEEE Trans. Netw. Sci. Eng."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tnse.2025.3641579","type":"journal-article","created":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T18:34:42Z","timestamp":1765305282000},"page":"4596-4615","source":"Crossref","is-referenced-by-count":4,"title":["Drone-Aided Secure Task Offloading Optimization for Internet of Vehicles: Review, Challenges and Method"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-9263-1596","authenticated-orcid":false,"given":"Ye","family":"Wang","sequence":"first","affiliation":[{"name":"School of Cyber Science and Technology, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3170-8952","authenticated-orcid":false,"given":"Jingjing","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3189-4222","authenticated-orcid":false,"given":"Jianrui","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9449-4854","authenticated-orcid":false,"given":"Xiangwang","family":"Hou","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1668-0528","authenticated-orcid":false,"given":"Ziyang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronic Information Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunxiao","family":"Jiang","sequence":"additional","affiliation":[{"name":"Tsinghua Space Center, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2022.05.016"},{"issue":"3","key":"ref2","first-page":"1","article-title":"Vehicular communications, networks, and applications","volume":"14","author":"Zhuang","year":"2016","journal-title":"ZTE Commun."},{"issue":"3","key":"ref3","first-page":"56","article-title":"Tensor decomposition-based channel estimation and sensing for millimeter wave MIMO-OFDM V2I systems","volume":"22","author":"Wang","year":"2024","journal-title":"ZTE Commun."},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3230430"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3259394"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MCOMSTD.001.2000017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2016.7470933"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2906789"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3653451"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2024.3459037"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.016.2300547"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2025.3613672"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/taes.2025.3612352"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2025.3582058"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2019.2930521"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.2400259"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2025.3575196"},{"key":"ref18","article-title":"Multi-objective aerial IRS-assisted ISAC optimization via generative AI-enhanced deep reinforcement learning","author":"Xie","year":"2025"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2023.3321048"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2024.3521885"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3370152"},{"key":"ref22","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lowe","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1287\/moor.27.4.819.297"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-04105-y"},{"key":"ref25","article-title":"Dealing with non-stationarity in multi-agent deep reinforcement learning","author":"Papoudakis"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1900661"},{"key":"ref27","first-page":"4295","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rashid","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref29","first-page":"5887","article-title":"Qtran: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Son","year":"2019"},{"key":"ref30","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"Proc. Int. Conf. Auton. Agents MultiAgent Syst.","author":"Sunehag","year":"2018"},{"key":"ref31","first-page":"10199","article-title":"Weighted QMIX: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rashid","year":"2020"},{"key":"ref32","first-page":"1","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2021"},{"key":"ref33","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu","year":"2022"},{"key":"ref34","first-page":"1","article-title":"Trust region policy optimisation in multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kuba","year":"2022"},{"key":"ref35","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Iqbal","year":"2019"},{"key":"ref36","first-page":"1","article-title":"DOP: Off-policy multi-agent decomposed policy gradients","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2020"},{"key":"ref37","first-page":"7265","article-title":"Learning attentional communication for multi-agent cooperation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jiang","year":"2018"},{"key":"ref38","first-page":"1538","article-title":"TarMAC: Targeted multi-agent communication","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Das","year":"2019"},{"key":"ref39","first-page":"1","article-title":"MAVEN: Multi-agent variational exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mahajan","year":"2019"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2018.01.002"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3457538"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"issue":"285","key":"ref44","first-page":"1","article-title":"OmniSafe: An infrastructure for accelerating safe reinforcement learning research","volume":"25","author":"Ji","year":"2024","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"ref45","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garcia","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"ref46","article-title":"Concrete problems in AI safety","author":"Amodei","year":"2016"},{"key":"ref47","article-title":"A survey of constraint formulations in safe reinforcement learning","author":"Wachi","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref49","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Achiam","year":"2017"},{"key":"ref50","first-page":"1","article-title":"Reward constrained policy optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tessler","year":"2019"},{"key":"ref51","first-page":"19039","article-title":"Safe reinforcement learning via curriculum induction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Turchetta","year":"2020"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3070252"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-015-9467-7"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2638961"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref56","first-page":"1231","article-title":"Policy gradients with variance related risk criteria","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tamar","year":"2012"},{"key":"ref57","first-page":"483","article-title":"Cautious reinforcement learning with logical constraints","volume-title":"Proc. Int. Conf. Auton. Agents Multiagent Syst.","author":"Hasanbeig","year":"2020"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12107"},{"key":"ref59","article-title":"Benchmarking safe exploration in deep reinforcement learning","author":"Ray","year":"2019"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2023.103905"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3332956"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3228811"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2945640"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2973651"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.bcra.2022.100087"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2025.3545444"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2024.3427814"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761212"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2021.3075530"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2023.3272351"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2018.8648004"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/tvt.2025.3552950"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3052979"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3016694"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2024.3476168"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3385414"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3437785"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3232841"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2021.3060169"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2022.3171600"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/tcomm.2025.3581093"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2024.3433457"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2024.3446667"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2020.3036871"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2021.3106955"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2021.3103124"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2024.3432765"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2024.3481061"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3370553"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3441236"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.2000292"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3015210"}],"container-title":["IEEE Transactions on Network Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488902\/11264281\/11288078.pdf?arnumber=11288078","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,25]],"date-time":"2025-12-25T05:42:36Z","timestamp":1766641356000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11288078\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":92,"URL":"https:\/\/doi.org\/10.1109\/tnse.2025.3641579","relation":{},"ISSN":["2327-4697","2334-329X"],"issn-type":[{"value":"2327-4697","type":"electronic"},{"value":"2334-329X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}