{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T17:41:30Z","timestamp":1770918090728,"version":"3.50.1"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Spanish Ministry of Science, Innovation and Universities","award":["TEC2017-89925-R"],"award-info":[{"award-number":["TEC2017-89925-R"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Veh. Technol."],"published-print":{"date-parts":[[2019,5]]},"DOI":"10.1109\/tvt.2019.2913695","type":"journal-article","created":{"date-parts":[[2019,5,24]],"date-time":"2019-05-24T02:23:41Z","timestamp":1558664621000},"page":"4295-4305","source":"Crossref","is-referenced-by-count":42,"title":["Decentralized Scheduling for Cooperative Localization With Deep Reinforcement Learning"],"prefix":"10.1109","volume":"68","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5511-4396","authenticated-orcid":false,"given":"Bile","family":"Peng","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2494-6872","authenticated-orcid":false,"given":"Gonzalo","family":"Seco-Granados","sequence":"additional","affiliation":[]},{"given":"Erik","family":"Steinmetz","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5274-2933","authenticated-orcid":false,"given":"Markus","family":"Frohle","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1298-6159","authenticated-orcid":false,"given":"Henk Wymeersch","family":"Wymeersch","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","author":"kay","year":"1993","journal-title":"Fundamentals of Statistical Signal Processing Estimation Theory"},{"key":"ref38","article-title":"Deep decentralized multi-task multi-agent reinforcement learning under partial observability","author":"omidshafiei","year":"2017"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/MVT.2018.2811185"},{"key":"ref31","article-title":"Deep reinforcement learning for distributed dynamic power allocation in wireless networks","author":"nasir","year":"2018"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2018.2832219"},{"key":"ref37","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","author":"foerster","year":"2017"},{"key":"ref36","article-title":"Deep recurrent q-learning for partially observable MDPs","author":"hausknecht","year":"0","journal-title":"Proc 2015 AAAI Fall Symp Series"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888912000057"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2013.042313.130218"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2016.1500356WC"},{"key":"ref12","author":"sutton","year":"1998","journal-title":"et\ufffdal"},{"key":"ref13","article-title":"Deep reinforcement learning: An overview","author":"li","year":"2017"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098843"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230551"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8485853"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2894437"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2760281"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2016.11.015"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2011.08.007"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2879361"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2002.1007796"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2018.10.023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2008.2008853"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2017.8254101"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2872928"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2016.2580504"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2014.2369631"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2017.1600374"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2012.6364478"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/s17020271"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref22","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"0","journal-title":"Proc 12th Int Conf Neural Inf Process Syst"},{"key":"ref21","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2012.2205381"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/DYSPAN.2008.82"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.5465\/AMR.2003.9416096"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2005.843547"},{"key":"ref44","article-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","author":"abadi","year":"2015"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2011.2165211"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2015.2430293"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2010.2059055"}],"container-title":["IEEE Transactions on Vehicular Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/25\/8723653\/08701533.pdf?arnumber=8701533","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:41:09Z","timestamp":1657744869000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8701533\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":44,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tvt.2019.2913695","relation":{},"ISSN":["0018-9545","1939-9359"],"issn-type":[{"value":"0018-9545","type":"print"},{"value":"1939-9359","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,5]]}}}