{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T23:58:01Z","timestamp":1770335881187,"version":"3.49.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"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":[],"published-print":{"date-parts":[[2020,6]]},"DOI":"10.1109\/iwqos49365.2020.9212868","type":"proceedings-article","created":{"date-parts":[[2020,10,6]],"date-time":"2020-10-06T20:03:04Z","timestamp":1602014584000},"page":"1-10","source":"Crossref","is-referenced-by-count":19,"title":["A Deep Reinforcement Learning Approach for Online Computation Offloading in Mobile Edge Computing"],"prefix":"10.1109","author":[{"given":"Yameng","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Tong","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Yanmin","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Yuanyuan","family":"Yang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref30","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2019.2928811"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2017.2725277"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737543"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2016.2612038"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2869954"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2017.2760160"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737560"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2018.8422661"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2014.2345410"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/BF01130406"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1126\/science.153.3731.34"},{"key":"ref4","first-page":"1","volume":"11","author":"hu","year":"2015","journal-title":"Mobile edge computing A key technology towards 5G"},{"key":"ref27","first-page":"807","article-title":"Rectified linear units improve restricted boltzmann machines","author":"nair","year":"0","journal-title":"Proceedings of the 27th International Conference on Machine Learning (ICML-10)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2017.2696539"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8485977"},{"key":"ref29","first-page":"2467","article-title":"Wireless and computing resource allocation for selfish computation offloading in edge computing","author":"jo\u0161ilo","year":"0","journal-title":"IEEE INFOCOM 2019-IEEE Conference on Computer Communications IEEE"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2745201"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2893094"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2019.02.008"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2240674"},{"key":"ref9","article-title":"Optimized computation offloading performance in virtual edge computing systems via deep reinforcement learning","author":"chen","year":"2018","journal-title":"IEEE Internet of Things Journal"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.pmcj.2009.07.007"},{"key":"ref20","volume":"135","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref24","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":"ref23","author":"mnih","year":"2013","journal-title":"Playing atari with deep reinforcement learning"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref25","article-title":"Deep reinforcement learning with double q-learning","author":"van hasselt","year":"0","journal-title":"THIRTIETH AAAI Conference on Artificial Intelligence"}],"event":{"name":"2020 IEEE\/ACM 28th International Symposium on Quality of Service (IWQoS)","location":"Hang Zhou, China","start":{"date-parts":[[2020,6,15]]},"end":{"date-parts":[[2020,6,17]]}},"container-title":["2020 IEEE\/ACM 28th International Symposium on Quality of Service (IWQoS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9203768\/9212810\/09212868.pdf?arnumber=9212868","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T21:50:40Z","timestamp":1656453040000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9212868\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/iwqos49365.2020.9212868","relation":{},"subject":[],"published":{"date-parts":[[2020,6]]}}}