{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T16:12:26Z","timestamp":1769184746465,"version":"3.49.0"},"reference-count":28,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100019923","name":"DEVCOM Army Research Laboratory","doi-asserted-by":"publisher","award":["W911NF-17-2-0196"],"award-info":[{"award-number":["W911NF-17-2-0196"]}],"id":[{"id":"10.13039\/100019923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Signal Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tsp.2025.3642042","type":"journal-article","created":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T18:48:10Z","timestamp":1765478890000},"page":"5348-5361","source":"Crossref","is-referenced-by-count":0,"title":["Track-MDP: Reinforcement Learning for Target Tracking With Controlled Sensing"],"prefix":"10.1109","volume":"73","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5690-3662","authenticated-orcid":false,"given":"Adarsh M.","family":"Subramaniam","sequence":"first","affiliation":[{"name":"Electrical & Computer Engineering Department and the Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Urbana, IL, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3828-2193","authenticated-orcid":false,"given":"Argyrios","family":"Gerogiannis","sequence":"additional","affiliation":[{"name":"Electrical & Computer Engineering Department and the Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Urbana, IL, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3920-7442","authenticated-orcid":false,"given":"James Z.","family":"Hare","sequence":"additional","affiliation":[{"name":"DEVCOM Army Research Laboratory, Adelphi, MD, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5490-0037","authenticated-orcid":false,"given":"Venugopal V.","family":"Veeravalli","sequence":"additional","affiliation":[{"name":"Electrical & Computer Engineering Department and the Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Urbana, IL, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890122"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3419755"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2011.6134321"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2009.934469"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2003.1208965"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1002\/0471221279"},{"key":"ref7","volume-title":"Tracking and Data Fusion.","author":"Bar-Shalom","year":"2011"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1017\/9781107185920"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2003.823141"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2011.2159496"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2007.912265"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2018.2814576"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2289881"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3101018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2023.3327885"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2567"},{"key":"ref17","first-page":"193","article-title":"Reinforcement learning of POMDPs using spectral methods","volume-title":"Proc. 29th Annu. Conf. Learn. Theory, Ser. Proc. Mach. Learn. Res.","volume":"49","author":"Azizzadenesheli","year":"2016"},{"issue":"5","key":"ref18","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1016\/j.dsp.2005.02.005","article-title":"Sensor scheduling for target tracking: A Monte Carlo sampling approach","volume":"16","author":"He","year":"2006","journal-title":"Digit. Signal Process."},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11276-014-0762-6"},{"issue":"3","key":"ref20","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1287\/moor.12.3.441","article-title":"The complexity of Markov decision processes","volume":"12","author":"Papadimitriou","year":"1987","journal-title":"Math. Oper. Res."},{"key":"ref21","article-title":"On the complexity of solving Markov decision problems","author":"Littman","year":"2013"},{"key":"ref22","article-title":"Near-optimal regret bounds for reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"21","author":"Auer","year":"2008"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50052-9"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2011.2167964"},{"issue":"2","key":"ref25","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1287\/opre.26.2.282","article-title":"The optimal control of partially observable Markov processes over the infinite horizon: Discounted costs","volume":"26","author":"Sondik","year":"1978","journal-title":"Oper. Res."},{"key":"ref26","volume-title":"Reinforcement Learning: An Introduction.","author":"Sutton","year":"2018"},{"key":"ref27","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","volume":"48","author":"Mnih","year":"2016"},{"key":"ref28","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"}],"container-title":["IEEE Transactions on Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/78\/10807692\/11298488.pdf?arnumber=11298488","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T21:04:21Z","timestamp":1769115861000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11298488\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/tsp.2025.3642042","relation":{},"ISSN":["1053-587X","1941-0476"],"issn-type":[{"value":"1053-587X","type":"print"},{"value":"1941-0476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}