{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:05:41Z","timestamp":1775228741045,"version":"3.50.1"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Plan","award":["2018YFB1003803"],"award-info":[{"award-number":["2018YFB1003803"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61802450"],"award-info":[{"award-number":["61802450"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61722214"],"award-info":[{"award-number":["61722214"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2018A030313005"],"award-info":[{"award-number":["2018A030313005"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Program for Guangdong Introducing Innovative and Entrepreneurial Teams","award":["2017ZT07X355"],"award-info":[{"award-number":["2017ZT07X355"]}]},{"DOI":"10.13039\/100016691","name":"Guangdong Provincial Pearl River Talents Program","doi-asserted-by":"publisher","award":["2019QN01X130"],"award-info":[{"award-number":["2019QN01X130"]}],"id":[{"id":"10.13039\/100016691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2021,5,1]]},"DOI":"10.1109\/tpds.2020.3042599","type":"journal-article","created":{"date-parts":[[2020,12,10]],"date-time":"2020-12-10T00:05:48Z","timestamp":1607558748000},"page":"1085-1101","source":"Crossref","is-referenced-by-count":109,"title":["Distributed and Collective Deep Reinforcement Learning for Computation Offloading: A Practical Perspective"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9322-9060","authenticated-orcid":false,"given":"Xiaoyu","family":"Qiu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5211-4235","authenticated-orcid":false,"given":"Weikun","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4430-7904","authenticated-orcid":false,"given":"Wuhui","family":"Chen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7872-7718","authenticated-orcid":false,"given":"Zibin","family":"Zheng","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2745201"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.4249\/scholarpedia.1965"},{"key":"ref33","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"mcmahan","year":"2016"},{"key":"ref32","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"CoRR"},{"key":"ref31","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref30","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2015.2409256"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8486403"},{"key":"ref35","article-title":"Revisiting distributed synchronous SGD","author":"chen","year":"2016"},{"key":"ref34","article-title":"Challenges of real-world reinforcement learning","author":"dulac-arnold","year":"2019"},{"key":"ref10","article-title":"IMPALA: Scalable distributed deep-RL with importance weighted actor-learner architectures","author":"espeholt","year":"2018","journal-title":"CoRR"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2924015"},{"key":"ref11","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"salimans","year":"2017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2018.2803826"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2926979"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2018.09.006"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2019.01.003"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2917890"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2933445"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2018.2883991"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2018.07.050"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2012.6195685"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2866945"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2015.2487344"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2018.2871449"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2017.2720741"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref7","article-title":"ProxylessNAS: Direct neural architecture search on target task and hardware","author":"cai","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/FiCloud.2017.24"},{"key":"ref9","first-page":"2775","article-title":"Bridging the gap between value and policy based reinforcement learning","author":"nachum","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2017.12.048"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2894437"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2894403"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2019.8885745"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2893925"},{"key":"ref24","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref41","first-page":"267","article-title":"Approximately optimal approximate reinforcement learning","volume":"2","author":"kakade","year":"2002","journal-title":"Proc 19th Int Conf Mach Learn"},{"key":"ref23","article-title":"Distributed deep Q-learning","author":"ong","year":"2015"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2876279"},{"key":"ref25","article-title":"Distributed distributional deterministic policy gradients","author":"barth-maron","year":"2018"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/9275496\/09288861.pdf?arnumber=9288861","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:27Z","timestamp":1652194227000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9288861\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,1]]},"references-count":42,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2020.3042599","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,1]]}}}