{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T02:19:46Z","timestamp":1785809986443,"version":"3.56.0"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Plan of China","award":["2019YFB1405402"],"award-info":[{"award-number":["2019YFB1405402"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2023,6,1]]},"DOI":"10.1109\/tmc.2022.3141080","type":"journal-article","created":{"date-parts":[[2022,1,7]],"date-time":"2022-01-07T20:34:49Z","timestamp":1641587689000},"page":"3425-3443","source":"Crossref","is-referenced-by-count":105,"title":["Large-Scale Computation Offloading Using a Multi-Agent Reinforcement Learning in Heterogeneous Multi-Access Edge Computing"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8896-3420","authenticated-orcid":false,"given":"Zhen","family":"Gao","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Northeastern University, Shenyang, Liaoning, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5451-9228","authenticated-orcid":false,"given":"Lei","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Northeastern University, Shenyang, Liaoning, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3534-0745","authenticated-orcid":false,"given":"Yu","family":"Dai","sequence":"additional","affiliation":[{"name":"School of College of Software, Northeastern University, Shenyang, Liaoning, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2019.02.050"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2997832"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3069911"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3020659"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3081694"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3020680"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.2986615"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2968951"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3009540"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2019.10.021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737385"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2913162"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11276-021-02632-z"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3064995"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3026862"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3039514"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3040768"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM38437.2019.9013115"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2020.3036871"},{"key":"ref20","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"Lowe","year":"2017","journal-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst."},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3046737"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3036962"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1186\/s13638-020-01801-6"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3023936"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3042599"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3050804"},{"key":"ref27","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","author":"Sunehag","year":"2018","journal-title":"Proc. 17th Int. Conf. Auton. Agents MultiAgent Syst."},{"key":"ref28","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref29","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2016","journal-title":"Proc. Int. Conf. Learn. Representations Poster"},{"key":"ref30","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.physd.2019.132306"},{"key":"ref32","article-title":"Delay-aware multi-agent reinforcement learning for cooperative and competitive environments","author":"Chen","year":"2020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.04.015"},{"key":"ref34","article-title":"UPDet: Universal multi-agent reinforcement learning via policy decoupling with transformers","author":"Hu","year":"2020","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref35","first-page":"1741","article-title":"Learning transferable cooperative behavior in multi-agent teams","author":"Agarwal","year":"2020","journal-title":"Proc. 19th Int. Conf. Auton. Agents MultiAgent Syst."},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2021.3057960"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2021.3140000"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3057046"},{"key":"ref39","article-title":"Concurrent meta reinforcement learning","author":"Parisotto","year":"2019"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2018.2823329"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7755\/10120635\/09674824.pdf?arnumber=9674824","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T00:17:47Z","timestamp":1705018667000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9674824\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":40,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2022.3141080","relation":{},"ISSN":["1536-1233","1558-0660","2161-9875"],"issn-type":[{"value":"1536-1233","type":"print"},{"value":"1558-0660","type":"electronic"},{"value":"2161-9875","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,1]]}}}