{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T22:16:46Z","timestamp":1769552206344,"version":"3.49.0"},"reference-count":31,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"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":["61671351"],"award-info":[{"award-number":["61671351"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61601340"],"award-info":[{"award-number":["61601340"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014219","name":"National Science Fund for Distinguished Young Scholars","doi-asserted-by":"publisher","award":["61525105"],"award-info":[{"award-number":["61525105"]}],"id":[{"id":"10.13039\/501100014219","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fund for Foreign Scholars in University Research and Teaching Programs","award":["B18039"],"award-info":[{"award-number":["B18039"]}]},{"name":"Shaanxi Innovation Team Project"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Systems Journal"],"published-print":{"date-parts":[[2021,3]]},"DOI":"10.1109\/jsyst.2020.2984774","type":"journal-article","created":{"date-parts":[[2020,5,12]],"date-time":"2020-05-12T00:04:55Z","timestamp":1589241895000},"page":"1264-1274","source":"Crossref","is-referenced-by-count":30,"title":["Data-Driven Simultaneous Multibeam Power Allocation: When Multiple Targets Tracking Meets Deep Reinforcement Learning"],"prefix":"10.1109","volume":"15","author":[{"given":"Yuchun","family":"Shi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Jiu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junkun","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongwei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref31","first-page":"2450","article-title":"Recurrent world models facilitate policy evolution","author":"ha","year":"0","journal-title":"Proc 32nd Conf Neural Inf Process Syst"},{"key":"ref30","first-page":"19","article-title":"Valiant load-balancing: Building networks that can support all traffic matrices","author":"shen","year":"2010"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/78.668800"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2004.1309993"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2014.2371774"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1979.1102177"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"481","DOI":"10.1109\/TAC.2009.2012975","article-title":"Markov chain Monte Carlo data association for multi-target tracking","volume":"54","author":"oh","year":"2009","journal-title":"IEEE Trans Autom Control"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/RADAR.2010.5494383"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2006.1642582"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref18","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"},{"key":"ref19","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref28","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc 3rd Int Conf Learn Represent"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/78.978386"},{"key":"ref27","author":"ristic","year":"2004","journal-title":"Beyond the Kalman Filter Particle Filters for Tracking Applications"},{"key":"ref3","author":"stone","year":"1999","journal-title":"Bayesian Multiple Target Tracking"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1109\/MSP.2007.904812","article-title":"MIMO radar with colocated antennas","volume":"24","author":"stoica","year":"2007","journal-title":"IEEE Signal Process Mag"},{"key":"ref29","author":"liggins","year":"2009","journal-title":"Handbook of Multisensor Data Fusion Theory and Practice"},{"key":"ref5","article-title":"Ubiquitous MIMO multifunction digital array radar and the role of time-energy management in radar","author":"rabideau","year":"2003"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2011.2144976"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2012.6237605"},{"key":"ref2","author":"blackman","year":"1986","journal-title":"Multiple-Target Tracking with Radar Applications"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2011.2174989"},{"key":"ref1","first-page":"1509","article-title":"A Bayesian approach to multiple target detection and tracking","volume":"55","author":"morelande","year":"2006","journal-title":"IEEE Trans Signal Process"},{"key":"ref20","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"0","journal-title":"Proc 4th Int Conf Learn Represent"},{"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","first-page":"-387i","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"0","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1002\/0471221104","author":"van trees","year":"2002","journal-title":"Optimum Array Processing Detection Estimation and Modulation Theory Part IV"},{"key":"ref23","author":"van trees","year":"1971","journal-title":"Detection Estimation and Modulation Theory Part III"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2005.1561880"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/78.928687"}],"container-title":["IEEE Systems Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4267003\/9373997\/09091081.pdf?arnumber=9091081","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,30]],"date-time":"2023-09-30T22:59:45Z","timestamp":1696114785000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9091081\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3]]},"references-count":31,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/jsyst.2020.2984774","relation":{},"ISSN":["1932-8184","1937-9234","2373-7816"],"issn-type":[{"value":"1932-8184","type":"print"},{"value":"1937-9234","type":"electronic"},{"value":"2373-7816","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3]]}}}