{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T16:21:28Z","timestamp":1759335688861,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,6]],"date-time":"2023-06-06T00:00:00Z","timestamp":1686009600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,6]],"date-time":"2023-06-06T00:00:00Z","timestamp":1686009600000},"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":[[2023,6,6]]},"DOI":"10.1109\/eucnc\/6gsummit58263.2023.10188325","type":"proceedings-article","created":{"date-parts":[[2023,7,26]],"date-time":"2023-07-26T18:09:41Z","timestamp":1690394981000},"page":"623-628","source":"Crossref","is-referenced-by-count":1,"title":["SeqDQN: Multi-Agent Deep Reinforcement Learning for Uplink URLLC with Strict Deadlines"],"prefix":"10.1109","author":[{"given":"Beno\u00eet-Marie","family":"Robaglia","sequence":"first","affiliation":[{"name":"LTCI, Telecom Paris Institut Polytechnique de Paris"}]},{"given":"Marceau","family":"Coupechoux","sequence":"additional","affiliation":[{"name":"LTCI, Telecom Paris Institut Polytechnique de Paris"}]},{"given":"Dimitrios","family":"Tsilimantos","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co. Ltd.,Advanced Wireless Technology Lab Paris Research Center"}]},{"given":"Apostolos","family":"Destounis","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co. Ltd.,Advanced Wireless Technology Lab Paris Research Center"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"sunehag","year":"2018","journal-title":"AAMAS"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/MILCOM.2018.8599723"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/ISWCS.2019.8877253"},{"key":"ref15","article-title":"Cooperative multi-agent reinforcement learning based distributed dynamic spectrum access in cognitive radio networks","author":"tan","year":"2021","journal-title":"ArXiv"},{"key":"ref14","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2018","journal-title":"ICML"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.3115\/v1\/W14-4012"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/TWC.2020.2984227"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/TAC.2016.2598476"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/JIOT.2018.2872441"},{"key":"ref21","article-title":"Deep Recurrent Q-learning for Partially Observable MDPs","author":"hausknecht","year":"0","journal-title":"AAAI Fall Symp"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/TCOMM.2017.2771478"},{"key":"ref1","first-page":"52065394","article-title":"Ultra-reliable low-latency 5g for industrial automation","volume":"2","author":"brown","year":"2018","journal-title":"QUALCOMM Technical Report"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1007\/978-3-031-79257-1"},{"key":"ref16","first-page":"471","author":"oliehoek","year":"2012","journal-title":"Decentralized POMDPs"},{"key":"ref19","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"NeurIPS"},{"year":"0","journal-title":"3rd Generation Partnership Project (3GPP) TR 38 889","article-title":"Study on physical layer enhancements for NR ultra-reliable and low latency case (URLLC)","key":"ref18"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/GLOBECOM46510.2021.9685561"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/COMST.2021.3063822"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1145\/1024916.1024920"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/MCOM.2018.1701178"},{"key":"ref6","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"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/COMST.2020.2988293"}],"event":{"name":"2023 Joint European Conference on Networks and Communications & 6G Summit (EuCNC\/6G Summit)","start":{"date-parts":[[2023,6,6]]},"location":"Gothenburg, Sweden","end":{"date-parts":[[2023,6,9]]}},"container-title":["2023 Joint European Conference on Networks and Communications & 6G Summit (EuCNC\/6G Summit)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10187889\/10188221\/10188325.pdf?arnumber=10188325","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,14]],"date-time":"2023-08-14T17:38:16Z","timestamp":1692034696000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10188325\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,6]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/eucnc\/6gsummit58263.2023.10188325","relation":{},"subject":[],"published":{"date-parts":[[2023,6,6]]}}}