{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T15:29:17Z","timestamp":1781018957266,"version":"3.54.1"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"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":["61671089"],"award-info":[{"award-number":["61671089"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1109\/jiot.2019.2935543","type":"journal-article","created":{"date-parts":[[2019,8,15]],"date-time":"2019-08-15T19:59:14Z","timestamp":1565899154000},"page":"10119-10133","source":"Crossref","is-referenced-by-count":69,"title":["Multiuser Resource Control With Deep Reinforcement Learning in IoT Edge Computing"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7828-0415","authenticated-orcid":false,"given":"Lei","family":"Lei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huijuan","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiong","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8531-6762","authenticated-orcid":false,"given":"Kan","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0608-065X","authenticated-orcid":false,"given":"Wei","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4890-0748","authenticated-orcid":false,"given":"Xianbin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/VTCFall.2016.7880951"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2342509.2342513"},{"key":"ref33","author":"foerster","year":"2018","journal-title":"Stabilising experience replay for deep multi-agent reinforcement learning"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2019.2902661"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2012.6231164"},{"key":"ref36","author":"hernandez-leal","year":"2019","journal-title":"A Survey of Learning in Multiagent Environments Dealing With Non-Stationarity"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref34","article-title":"Deep reinforcement learning for multi-agent systems: A review of challenges, solutions and applications","author":"nguyen","year":"2019","journal-title":"arXiv preprint arXiv 1812 11467"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2016.7510999"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2664418"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2717986"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2017.2760186"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2010.2050062"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2016.2558146"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2016.7541539"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SAHCN.2016.7733009"},{"key":"ref17","first-page":"2885","article-title":"A semi-Markovian decision process based control method for offloading tasks from mobile devices to the cloud","author":"chen","year":"2013","journal-title":"Proc IEEE Global Communication Conf (GLOBECOM)"},{"key":"ref18","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2018.8377343"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2805263"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.dcan.2018.10.003"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2778504"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2783374"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCW.2018.8403711"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2764475"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2745201"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2812299"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2750180"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2819690"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2767608"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2013.020413.120457"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2900550"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2015.2444791"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2878435"},{"key":"ref41","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2876279"},{"key":"ref26","author":"chen","year":"2018","journal-title":"Decentralized Computation Offloading for Multi-User Mobile Edge Computing A Deep Reinforcement Learning Approach"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2018.2805718"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6488907\/8931267\/08802256.pdf?arnumber=8802256","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,25]],"date-time":"2022-09-25T19:07:57Z","timestamp":1664132877000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8802256\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":41,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2019.2935543","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,12]]}}}