{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T20:17:00Z","timestamp":1778271420808,"version":"3.51.4"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"U.K. Commonwealth Scholarship Commission"},{"name":"NTU-SUG","award":["025661-00010"],"award-info":[{"award-number":["025661-00010"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Wireless Commun."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/twc.2026.3687667","type":"journal-article","created":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T19:38:05Z","timestamp":1777923485000},"page":"16229-16244","source":"Crossref","is-referenced-by-count":0,"title":["Deep Reinforcement Learning-Based Access Point Selection in Cell-Free Massive MIMO With Behavior Cloning"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9723-8813","authenticated-orcid":false,"given":"Dativa K.","family":"Tizikara","sequence":"first","affiliation":[{"name":"Department of Computer and Communications Engineering, Makerere University, Kampala, Uganda"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7642-1755","authenticated-orcid":false,"given":"Daniel K. C.","family":"So","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, The University of Manchester, Manchester, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5280-384X","authenticated-orcid":false,"given":"Zhiguo","family":"Ding","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Nanyang Ave, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3123267"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2024.3393514"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1561\/2000000109"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2952117"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2020.2987311"},{"key":"ref6","first-page":"1","article-title":"User-centric massive MIMO systems with hardening-based clusterization","volume-title":"Proc. WSA; 24th Int. ITG Workshop Smart Antennas","author":"Polegre"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ISWCS.2018.8491054"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3131465"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2017.2770215"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM42002.2020.9322341"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3118303"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2020.3036086"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF51394.2020.9443536"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2022.3186350"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2025.3547620"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM46510.2021.9685221"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3104743"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC60668.2024.10694529"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC51304.2022.9833939"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2021-Fall52928.2021.9625449"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2022.3196013"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2024.3387095"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMLCN.2023.3283228"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45041.2023.10279626"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2024.3424507"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2024.3411800"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2024.3494537"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2025-Spring65109.2025.11174418"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3512663"},{"key":"ref30","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"Vecerik","year":"2017","journal-title":"arXiv.1707.08817"},{"key":"ref31","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume-title":"Proc. Ann. Conf. Neural Inf. Process. Syst.","author":"Fujimoto"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.65109\/knri7638"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1093\/imaman\/dpae031"},{"key":"ref35","article-title":"A closer look at invalid action masking in policy gradient algorithms","volume-title":"Proc. Ann. FLAIRS Conf.","volume":"35","author":"Huang"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2655515"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3270299"},{"key":"ref38","article-title":"Deep reinforcement learning in large discrete action spaces","author":"Dulac-Arnold","year":"2016","journal-title":"arXiv.1512.07679"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref40","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref41","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":"ref42","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref43","article-title":"Continuous control with deep reinforcement learning","volume-title":"arXiv:1509.02971","author":"Lillicrap"},{"key":"ref44","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019","journal-title":"arXiv:1912.06680"},{"key":"ref45","article-title":"StarCraft II: A new challenge for reinforcement learning","author":"Yeo","year":"2017","journal-title":"arXiv:1708.04782"},{"key":"ref46","article-title":"Learn what not to learn: Action elimination with deep reinforcement learning","volume-title":"Proc. Ann. Conf. Neural Inf. Process. Syst.","author":"Zahavy"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CoG47356.2020.9231687"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3013"},{"key":"ref49","article-title":"Dynamic neighborhood construction for structured large discrete action spaces","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Akkerman"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07711-7"},{"key":"ref51","first-page":"620","article-title":"Loss of plasticity in continual deep reinforcement learning","volume-title":"Proc. Conf. Lifelong Learn. Agents","author":"Abbas"},{"key":"ref52","first-page":"3884","article-title":"On warm-starting neural network training","volume-title":"Proc. Ann. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Ash"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3164"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3439101"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3230041"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2933417"},{"key":"ref57","volume-title":"Twin Delayed DDPG","year":"2024"}],"container-title":["IEEE Transactions on Wireless Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7693\/11298242\/11505749.pdf?arnumber=11505749","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T19:42:27Z","timestamp":1778269347000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11505749\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/twc.2026.3687667","relation":{},"ISSN":["1536-1276","1558-2248"],"issn-type":[{"value":"1536-1276","type":"print"},{"value":"1558-2248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}