{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T02:53:58Z","timestamp":1768532038815,"version":"3.49.0"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1109\/tnse.2025.3577628","type":"journal-article","created":{"date-parts":[[2025,6,9]],"date-time":"2025-06-09T13:35:50Z","timestamp":1749476150000},"page":"1-18","source":"Crossref","is-referenced-by-count":4,"title":["Adaptive Edge Task Offloading via Parameterized Multi-Objective Reinforcement Learning with Hybrid Action Space"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-9099-2241","authenticated-orcid":false,"given":"Huimin","family":"Tong","sequence":"first","affiliation":[{"name":"Hikvision Research Institute, Hangzhou Hikvision Digital Technology Co., Ltd, Hangzhou, China"}]},{"given":"Cheng","family":"Chen","sequence":"additional","affiliation":[{"name":"Hikvision Research Institute, Hangzhou Hikvision Digital Technology Co., Ltd, Hangzhou, China"}]},{"given":"Weihao","family":"Jiang","sequence":"additional","affiliation":[{"name":"Hikvision Research Institute, Hangzhou Hikvision Digital Technology Co., Ltd, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7223-8849","authenticated-orcid":false,"given":"Ting","family":"Wang","sequence":"additional","affiliation":[{"name":"Engineering Research Center of Software\/Hardware Co-design Technology and Application, Ministry of Education; the Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China"}]},{"given":"Jiang","family":"Zhu","sequence":"additional","affiliation":[{"name":"Hikvision Research Institute, Hangzhou Hikvision Digital Technology Co., Ltd, Hangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3312676"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2024.3372892"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2022.3154760"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3372614"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3284217"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2023.3339468"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3301019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3461709"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3315334"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3416171"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2024.3368156"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2024.3379252"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2021.108177"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2023.3338015"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2024.3409207"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2024.3350710"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3333826"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3421541"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3390\/s23146448"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2022.3184835"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3327121"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3270967"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3395993"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45041.2023.10279699"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3492321.3519593"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2024.3372046"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2024.06.018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3378007"},{"key":"ref29","first-page":"1756","article-title":"Near on-policy experience sampling in multi-objective reinforcement learning","volume-title":"Proc. 21st Int. Conf. Auton. Agents Multiagent Syst.","author":"Wang","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2024.3489443"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3322748"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2023.3237854"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3119200"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2022.109137"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2021.09.028"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2020.3036871"},{"key":"ref37","first-page":"1552","article-title":"Computation offloading optimization in edge computing based on deep reinforcement learning","volume-title":"Proc. 5th Int. Conf. Mech., Control, Comput. Eng.","author":"Zhu","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3329643"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2024.3432893"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3329869"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119154"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3409367"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3209987"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3296774"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3141080"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3384405"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2024.3496902"},{"key":"ref48","article-title":"Multi-objective reinforcement learning: Convexity, stationarity and pareto optimality","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lu","year":"2023"},{"key":"ref49","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","volume":"80","author":"Haarnoja","year":"2018"},{"key":"ref50","article-title":"Parametrized deep Q-networks learning: Playing online battle arena with discrete-continuous hybrid action space","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xiong","year":"2018"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3023936"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CommNet63022.2024.10793350"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.dcan.2018.10.003"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/APWiMob51111.2021.9435258"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2023.3286578"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3238771"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CICT64037.2024.10899709"},{"key":"ref58","first-page":"11","article-title":"Dynamic weights in multi-objective deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Abels","year":"2019"},{"key":"ref59","article-title":"PD-MORL: Preference-driven multi-objective reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Basaklar","year":"2023"}],"container-title":["IEEE Transactions on Network Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488902\/6930788\/11027806.pdf?arnumber=11027806","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T04:39:43Z","timestamp":1761367183000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11027806\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/tnse.2025.3577628","relation":{},"ISSN":["2327-4697","2334-329X"],"issn-type":[{"value":"2327-4697","type":"electronic"},{"value":"2334-329X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}