{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T05:57:57Z","timestamp":1776232677227,"version":"3.50.1"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,28]],"date-time":"2023-05-28T00:00:00Z","timestamp":1685232000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,28]],"date-time":"2023-05-28T00:00:00Z","timestamp":1685232000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020AAA0107400,2021ZD0114600"],"award-info":[{"award-number":["2020AAA0107400,2021ZD0114600"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["40500-20103-222131"],"award-info":[{"award-number":["40500-20103-222131"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5,28]]},"DOI":"10.1109\/icc45041.2023.10279699","type":"proceedings-article","created":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T17:54:10Z","timestamp":1698083650000},"page":"4039-4044","source":"Crossref","is-referenced-by-count":7,"title":["Towards Efficient Task Offloading at the Edge Based on Meta-Reinforcement Learning with Hybrid Action Space"],"prefix":"10.1109","author":[{"given":"Zhao","family":"Yang","sequence":"first","affiliation":[{"name":"East China Normal University,MoE Engineering Research Center of Software\/Hardware Co-design Technology and Application, Shanghai Key Laboratory of Trustworthy Computing,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxiang","family":"Deng","sequence":"additional","affiliation":[{"name":"East China Normal University,MoE Engineering Research Center of Software\/Hardware Co-design Technology and Application, Shanghai Key Laboratory of Trustworthy Computing,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ting","family":"Wang","sequence":"additional","affiliation":[{"name":"East China Normal University,MoE Engineering Research Center of Software\/Hardware Co-design Technology and Application, Shanghai Key Laboratory of Trustworthy Computing,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haibin","family":"Cai","sequence":"additional","affiliation":[{"name":"East China Normal University,MoE Engineering Research Center of Software\/Hardware Co-design Technology and Application, Shanghai Key Laboratory of Trustworthy Computing,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2815360"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/COMSNETS51098.2021.9352931"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-021-03941-y"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2017.8057150"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2015.2487344"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2018.2867482"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tpds.2020.3042224"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tpds.2020.3014896"},{"key":"ref9","article-title":"Deep reinforcement learning in parame-terized action space","author":"Hausknecht","year":"2015","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2019.02.006"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/PIMRC.2017.8292514"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2891113"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2022.3163750"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/jiot.2018.2876279"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3004861"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2021.3087258"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/316"},{"key":"ref18","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Recurrent models of visual attention","volume":"27","author":"Mnih","year":"2014","journal-title":"Advances in neural information processing systems"}],"event":{"name":"ICC 2023 - IEEE International Conference on Communications","location":"Rome, Italy","start":{"date-parts":[[2023,5,28]]},"end":{"date-parts":[[2023,6,1]]}},"container-title":["ICC 2023 - IEEE International Conference on Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10278505\/10278554\/10279699.pdf?arnumber=10279699","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T09:02:58Z","timestamp":1709370178000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10279699\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,28]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icc45041.2023.10279699","relation":{},"subject":[],"published":{"date-parts":[[2023,5,28]]}}}