{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T03:17:50Z","timestamp":1782962270070,"version":"3.54.5"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"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":[[2021,12]]},"DOI":"10.1109\/globecom46510.2021.9685561","type":"proceedings-article","created":{"date-parts":[[2022,2,2]],"date-time":"2022-02-02T21:59:04Z","timestamp":1643839144000},"page":"1-6","source":"Crossref","is-referenced-by-count":7,"title":["Deep Reinforcement Learning for Scheduling Uplink IoT Traffic with Strict Deadlines"],"prefix":"10.1109","author":[{"given":"Benoit-Marie","family":"Robaglia","sequence":"first","affiliation":[{"name":"Paris Research Center, Huawei Technologies Co. Ltd.,Mathematical and Algorithmic Sciences Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Apostolos","family":"Destounis","sequence":"additional","affiliation":[{"name":"Paris Research Center, Huawei Technologies Co. Ltd.,Mathematical and Algorithmic Sciences Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marceau","family":"Coupechoux","sequence":"additional","affiliation":[{"name":"LTCI, Telecom Paris, Institut Polytechnique de Paris"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dimitrios","family":"Tsilimantos","sequence":"additional","affiliation":[{"name":"Paris Research Center, Huawei Technologies Co. Ltd.,Mathematical and Algorithmic Sciences Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.2984227"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MILCOM.2018.8599723"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904329"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2015.7295483"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1561\/9781680836219"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2807924"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCW.2019.8756759"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2018.8646405"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.2200\/S00507ED1V01Y201305CNT014"},{"key":"ref19","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2020.2988293"},{"key":"ref27","article-title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","author":"saxe","year":"2013","journal-title":"ArXiv Preprint"},{"key":"ref3","first-page":"368","article-title":"Coverage and capacity analysis of wireless m2m technologies for smart distribution grid services","author":"h\u00e4gerling","year":"0","journal-title":"2014 IEEE International Conference on Smart Grid Communications (SmartGridComm)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/49.840210"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1024916.1024920"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2013.01.010"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2872441"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2837382"},{"key":"ref20","article-title":"A closer look at invalid action masking in policy gradient algorithms","author":"huang","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref22","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref21","article-title":"Deep recurrent q-learning for partially observable mdps","author":"hausknecht","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref23","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref26","author":"mills-tettey","year":"2007","journal-title":"The Dynamic Hungarian Algorithm for the Assignment Problem With Changing Costs"},{"key":"ref25","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015","journal-title":"ArXiv Preprint"}],"event":{"name":"GLOBECOM 2021 - 2021 IEEE Global Communications Conference","location":"Madrid, Spain","start":{"date-parts":[[2021,12,7]]},"end":{"date-parts":[[2021,12,11]]}},"container-title":["2021 IEEE Global Communications Conference (GLOBECOM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9685019\/9685006\/09685561.pdf?arnumber=9685561","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T23:46:48Z","timestamp":1659484008000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9685561\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/globecom46510.2021.9685561","relation":{},"subject":[],"published":{"date-parts":[[2021,12]]}}}