{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T18:01:33Z","timestamp":1771696893577,"version":"3.50.1"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"17","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21A20456"],"award-info":[{"award-number":["U21A20456"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFB2900801"],"award-info":[{"award-number":["2021YFB2900801"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2023,9,1]]},"DOI":"10.1109\/jiot.2023.3264253","type":"journal-article","created":{"date-parts":[[2023,4,3]],"date-time":"2023-04-03T17:37:56Z","timestamp":1680543476000},"page":"15477-15487","source":"Crossref","is-referenced-by-count":17,"title":["Heuristically Assisted Multiagent RL-Based Framework for Computation Offloading and Resource Allocation of Mobile-Edge Computing"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5374-0323","authenticated-orcid":false,"given":"Xulong","family":"Li","sequence":"first","affiliation":[{"name":"Beijing Engineering and Technology Research Center for Convergence Networks and Ubiquitous Services, University of Science and Technology Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6655-9849","authenticated-orcid":false,"given":"Yunhui","family":"Qin","sequence":"additional","affiliation":[{"name":"School of Cyberspace Science and Technology, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3181-2816","authenticated-orcid":false,"given":"Jiahao","family":"Huo","sequence":"additional","affiliation":[{"name":"Beijing Engineering and Technology Research Center for Convergence Networks and Ubiquitous Services, University of Science and Technology Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2887-8395","authenticated-orcid":false,"given":"Wei","family":"Huangfu","sequence":"additional","affiliation":[{"name":"Beijing Engineering and Technology Research Center for Convergence Networks and Ubiquitous Services, University of Science and Technology Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2968951"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3036962"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM38437.2019.9013115"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1186\/s13638-020-01801-6"},{"key":"ref31","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"},{"key":"ref30","article-title":"Parametrized deep Q-networks learning: Reinforcement learning with discrete-continuous hybrid action space","author":"xiong","year":"2018","journal-title":"arXiv 1810 06394"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.2986615"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2890685"},{"key":"ref32","article-title":"Soft actor-critic algorithms and applications","author":"haarnoja","year":"2018","journal-title":"arXiv 1812 05905"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2240674"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2745201"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCC49849.2020.9238942"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.23919\/JCC.2020.09.017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2021-Spring51267.2021.9448922"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3040768"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2876279"},{"key":"ref23","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref26","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"arXiv 1706 02275"},{"key":"ref25","article-title":"A quantitative measure of fairness and discrimination","author":"jain","year":"1984"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2021-Spring51267.2021.9448637"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2021.3132103"},{"key":"ref21","first-page":"296","article-title":"Heuristic and meta-heuristic algorithms and their relevance to the real world: A survey","volume":"2","author":"desale","year":"2015","journal-title":"International Journal of Computer Engineering in Research Trends"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93025-1_4"},{"key":"ref29","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3063822"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2965898"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2020-Fall49728.2020.9348633"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2019.02.008"},{"key":"ref3","author":"hu","year":"2015","journal-title":"Mobile edge computing—A key technology towards 5G"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2935877"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2017.2699660"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6488907\/10227658\/10091485.pdf?arnumber=10091485","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T19:10:04Z","timestamp":1694459404000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10091485\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,1]]},"references-count":32,"journal-issue":{"issue":"17"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2023.3264253","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,1]]}}}