{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:13:05Z","timestamp":1775229185942,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,8,10]],"date-time":"2023-08-10T00:00:00Z","timestamp":1691625600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,10]],"date-time":"2023-08-10T00:00:00Z","timestamp":1691625600000},"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":[[2023,8,10]]},"DOI":"10.1109\/iccc57788.2023.10233668","type":"proceedings-article","created":{"date-parts":[[2023,9,5]],"date-time":"2023-09-05T17:28:28Z","timestamp":1693934908000},"page":"1-6","source":"Crossref","is-referenced-by-count":8,"title":["Online Container Scheduling for Low-Latency IoT Services in Edge Cluster Upgrade: A Reinforcement Learning Approach"],"prefix":"10.1109","author":[{"given":"Hanshuai","family":"Cui","sequence":"first","affiliation":[{"name":"Beijing Normal University,Institute of Artificial Intelligence and Future Networks,Zhuhai,China,519087"}]},{"given":"Zhiqing","family":"Tang","sequence":"additional","affiliation":[{"name":"Beijing Normal University,Institute of Artificial Intelligence and Future Networks,Zhuhai,China,519087"}]},{"given":"Jiong","family":"Lou","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China,200240"}]},{"given":"Weijia","family":"Jia","sequence":"additional","affiliation":[{"name":"Beijing Normal University,Institute of Artificial Intelligence and Future Networks,Zhuhai,China,519087"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2021.3066495"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511841224"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2018.2850026"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2014.2316834"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1109\/TNN.2004.842673","article-title":"Reinforcement learning: An introduction","volume":"16","author":"sutton","year":"2005","journal-title":"IEEE Transactions on Neural Networks"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3110412"},{"key":"ref20","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"sutton","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.est.2021.102913"},{"key":"ref22","author":"schulman","year":"2015","journal-title":"High-dimensional continuous control using generalized advantage estimation"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2019.06.010"},{"key":"ref21","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2021.3052837"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3001355"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2815360"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2892176"},{"key":"ref19","first-page":"8145","article-title":"Reinforcement learning in continuous time and space: A stochastic control approach","volume":"21","author":"wang","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2017.2787700"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SEAA.2018.00056"},{"key":"ref7","year":"0","journal-title":"Kubernetes"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2021.3112204"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2018.2871842"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2020.3033807"},{"key":"ref6","article-title":"Layer dependency-aware learning scheduling algorithms for containers in mobile edge computing","author":"tang","year":"2022","journal-title":"IEEE Transactions on Mobile Computing"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2019.2957804"}],"event":{"name":"2023 IEEE\/CIC International Conference on Communications in China (ICCC)","location":"Dalian, China","start":{"date-parts":[[2023,8,10]]},"end":{"date-parts":[[2023,8,12]]}},"container-title":["2023 IEEE\/CIC International Conference on Communications in China (ICCC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10233255\/10233122\/10233668.pdf?arnumber=10233668","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T17:56:24Z","timestamp":1695664584000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10233668\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,10]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/iccc57788.2023.10233668","relation":{},"subject":[],"published":{"date-parts":[[2023,8,10]]}}}