{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:09:09Z","timestamp":1740100149369,"version":"3.37.3"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004489","name":"Mitacs","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004489","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6]]},"DOI":"10.1109\/icc42927.2021.9500463","type":"proceedings-article","created":{"date-parts":[[2021,8,6]],"date-time":"2021-08-06T20:49:21Z","timestamp":1628282961000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["Structure-aware reinforcement learning for node-overload protection in mobile edge computing"],"prefix":"10.1109","author":[{"given":"Anirudha","family":"Jitani","sequence":"first","affiliation":[{"name":"McGill Univeristy,School of Computer Science,Montreal,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aditya","family":"Mahajan","sequence":"additional","affiliation":[{"name":"McGill Univeristy,Electrical and Computer Engineering,Montreal,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongwen","family":"Zhu","sequence":"additional","affiliation":[{"name":"Ericsson,Global AI Accelerator,Montreal,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hatem","family":"Abou-Zeid","sequence":"additional","affiliation":[{"name":"Ericsson,Ottawa,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emmanuel Thepie","family":"Fapi","sequence":"additional","affiliation":[{"name":"Ericsson,Global AI Accelerator,Montreal,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hakimeh","family":"Purmehdi","sequence":"additional","affiliation":[{"name":"Ericsson,Global AI Accelerator,Montreal,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref10"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"4005","DOI":"10.1109\/JIOT.2018.2876279","article-title":"Optimized computation offloading performance in virtual edge computing systems via deep reinforcement learning","volume":"6","author":"chen","year":"2018","journal-title":"IEEE Internet of Things Journal"},{"article-title":"Deep reinforcement learning for online offloading in wireless powered mobile-edge computing networks","year":"2018","author":"huang","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2019.1800971"},{"article-title":"Online reinforcement learning of optimal threshold policies for Markov decision processes","year":"2019","author":"roy","key":"ref14"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref15"},{"article-title":"Scalable trust-region method for deep reinforcement learning using kronecker-factored approximation","year":"2017","author":"wu","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6911(97)90015-3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2852330"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2785305"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2019.2916577"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2815360"},{"journal-title":"Dynamic Programming and Markov Processes","year":"1960","author":"howard","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1080\/03461238.1953.10419459"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2016.7541539"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2017.9"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"}],"event":{"name":"ICC 2021 - IEEE International Conference on Communications","start":{"date-parts":[[2021,6,14]]},"location":"Montreal, QC, Canada","end":{"date-parts":[[2021,6,23]]}},"container-title":["ICC 2021 - IEEE International Conference on Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9500243\/9500244\/09500463.pdf?arnumber=9500463","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:07:29Z","timestamp":1659485249000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9500463\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/icc42927.2021.9500463","relation":{},"subject":[],"published":{"date-parts":[[2021,6]]}}}