{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:45:17Z","timestamp":1784137517525,"version":"3.55.0"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61872147"],"award-info":[{"award-number":["61872147"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Plan","award":["CJGJZD20210408092400001"],"award-info":[{"award-number":["CJGJZD20210408092400001"]}]},{"name":"Dean\u2019s Fund of Engineering Research Center of Software\/Hardware Co-Design Technology and Application, Ministry of Education"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Wireless Commun."],"published-print":{"date-parts":[[2023,3]]},"DOI":"10.1109\/twc.2022.3207918","type":"journal-article","created":{"date-parts":[[2022,9,27]],"date-time":"2022-09-27T19:51:22Z","timestamp":1664308282000},"page":"1900-1914","source":"Crossref","is-referenced-by-count":68,"title":["Multi-Agent Reinforcement Learning for Dynamic Resource Management in 6G in-X Subnetworks"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8479-6530","authenticated-orcid":false,"given":"Xiao","family":"Du","sequence":"first","affiliation":[{"name":"Shanghai Key Laboratory of Trustworthy Computing, MoE Engineering Research Center of Software\/Hardware Co-Design Technology and Application, East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7223-8849","authenticated-orcid":false,"given":"Ting","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Trustworthy Computing, MoE Engineering Research Center of Software\/Hardware Co-Design Technology and Application, East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Feng","sequence":"additional","affiliation":[{"name":"Bell Laboratories, Nokia Shanghai Bell Corporation, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenhui","family":"Ye","sequence":"additional","affiliation":[{"name":"Bell Laboratories, Nokia Shanghai Bell Corporation, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7672-4043","authenticated-orcid":false,"given":"Tao","family":"Tao","sequence":"additional","affiliation":[{"name":"Bell Laboratories, Nokia Shanghai Bell Corporation, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6345-3873","authenticated-orcid":false,"given":"Lu","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1418-7465","authenticated-orcid":false,"given":"Yuanming","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, ShanghaiTech University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3922-0989","authenticated-orcid":false,"given":"Mingsong","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Trustworthy Computing, MoE Engineering Research Center of Software\/Hardware Co-Design Technology and Application, East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"European vision for the 6G network ecosystem","author":"Bernardos","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2019.1900271"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/6GSUMMIT49458.2020.9083877"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11276-020-02479-w"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2008.070227"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2011.2147784"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2014.6845058"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2015.7105641"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2716921"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2017.8006944"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2014.2328102"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2015.7421354"},{"key":"ref13","article-title":"Artificial neural networks-based machine learning for wireless networks: A tutorial","author":"Chen","year":"2017","journal-title":"arXiv:1710.02913"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2926625"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/GCWkshps50303.2020.9367532"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933962"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2961405"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2013.6590055"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/PIMRC.2018.8580784"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2013.2251604"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3036965"},{"key":"ref22","article-title":"A deep Q-learning method for downlink power allocation in multi-cell networks","author":"Ishfaq Ahmed","year":"2019","journal-title":"arXiv:1904.13032"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2015.2498925"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2017.7997440"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/NRSC.2017.7893487"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761431"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933973"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3117859"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3131534"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3051163"},{"key":"ref31","article-title":"Distributed deep reinforcement learning for adaptive medium access and modulation in shared spectrum","author":"Doshi","year":"2021","journal-title":"arXiv:2109.11723"},{"key":"ref32","first-page":"1","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lowe"},{"key":"ref33","first-page":"1538","article-title":"TarMAC: Targeted multi-agent communication","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Das"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6211"},{"key":"ref35","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"Proc. Int. Conf. Auto. Agents MultiAgent Syst.","author":"Sunehag"},{"key":"ref36","first-page":"4295","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rashid"},{"key":"ref37","first-page":"5887","article-title":"QTRAN: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Son"},{"key":"ref38","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","author":"Wang","year":"2020","journal-title":"arXiv:2008.01062"},{"key":"ref39","first-page":"4596","article-title":"Randomized entity-wise factorization for multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Iqbal"},{"key":"ref40","article-title":"Graph convolutional reinforcement learning","author":"Jiang","year":"2018","journal-title":"arXiv:1810.09202"},{"key":"ref41","article-title":"Graph convolutional value decomposition in multi-agent reinforcement learning","author":"Naderializadeh","year":"2020","journal-title":"arXiv:2010.04740"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/REDUNDANCY48165.2019.9003345"},{"key":"ref43","article-title":"Value function factorisation with hypergraph convolution for cooperative multi-agent reinforcement learning","author":"Bai","year":"2021","journal-title":"arXiv:2112.06771"},{"key":"ref44","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref45","article-title":"Categorical reparameterization with Gumbel-Softmax","author":"Jang","year":"2016","journal-title":"arXiv:1611.01144"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref48","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017","journal-title":"arXiv:1710.10903"},{"key":"ref49","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1002\/9781119471509.w5gref048"},{"key":"ref51","volume-title":"Google Colab","author":"Colab","year":"2022"},{"key":"ref52","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"}],"container-title":["IEEE Transactions on Wireless Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7693\/10064475\/09904510.pdf?arnumber=9904510","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T23:06:38Z","timestamp":1705964798000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9904510\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3]]},"references-count":52,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/twc.2022.3207918","relation":{},"ISSN":["1536-1276","1558-2248"],"issn-type":[{"value":"1536-1276","type":"print"},{"value":"1558-2248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3]]}}}