{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:34:29Z","timestamp":1788892469880,"version":"build-2803163510"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100018891","name":"Saab","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018891","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1109\/jstsp.2024.3386057","type":"journal-article","created":{"date-parts":[[2024,4,8]],"date-time":"2024-04-08T16:58:03Z","timestamp":1712595483000},"page":"737-751","source":"Crossref","is-referenced-by-count":25,"title":["Model-Based Online Learning for Active ISAC Waveform Optimization"],"prefix":"10.1109","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0589-0992","authenticated-orcid":false,"given":"Petteri","family":"Pulkkinen","sequence":"first","affiliation":[{"name":"Department of Information and Communications Engineering, Aalto University, Espoo, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1454-5928","authenticated-orcid":false,"given":"Visa","family":"Koivunen","sequence":"additional","affiliation":[{"name":"Department of Information and Communications Engineering, Aalto University, Espoo, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3156632"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2017.2666266"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2020.2973976"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/0471663085"},{"key":"ref5","volume-title":"An Introduction to Passive Radar","author":"Griffiths","year":"2017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3070399"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472362"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683655"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SAM48682.2020.9104262"},{"issue":"21","key":"ref10","doi-asserted-by":"crossref","DOI":"10.3390\/rs13214376","article-title":"Joint radar-communications exploiting optimized OFDM waveforms","volume":"13","author":"Ahmed","year":"2021","journal-title":"Remote Sens."},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2018.2884806"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICC40277.2020.9149408"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3327053"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3157371"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1561\/9781680831719"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1017\/9781108571401"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/RADAR.2018.8378616"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2020.3019605"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2021.3109110"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2018.8645080"},{"issue":"3","key":"ref22","doi-asserted-by":"crossref","DOI":"10.3390\/electronics11030441","article-title":"Reinforcement learning-based UAVs resource allocation for integrated sensing and communication (ISAC) system","volume":"11","author":"Wang","year":"2022","journal-title":"Electronics"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2022.3182034"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3124810"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095423"},{"key":"ref26","volume-title":"Constrained Markov Decision Processes","author":"Altman","year":"1999"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9747269"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO55093.2022.9909601"},{"key":"ref29","first-page":"12519","article-title":"When to trust your model: Model-based policy optimization","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Janner","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2338894"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2018.2809722"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933778"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1561\/2200000086"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-090419-075625"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1561\/0100000006"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2017.2676808"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2011.5751234"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2007.4383581"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2007.897047"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2005.844072"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF44664.2019.9049055"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-7566-5"},{"key":"ref44","first-page":"463","article-title":"Model-based reinforcement learning with value-targeted regression","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Ayoub","year":"2020"},{"key":"ref45","first-page":"4171","article-title":"Logarithmic regret for reinforcement learning with linear function approximation","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"He","year":"2021"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2012.2212414"},{"key":"ref47","first-page":"928","article-title":"Online convex programming and generalized infinitesimal gradient ascent","volume-title":"Proc. 28th Int. Conf. Int. Conf. Mach. Learn.","author":"Zinkevich","year":"2003"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1090\/mbk\/107"},{"key":"ref49","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2017"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4200690\/10832396\/10494366.pdf?arnumber=10494366","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T13:41:54Z","timestamp":1738849314000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10494366\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":49,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2024.3386057","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7]]}}}