{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:53:04Z","timestamp":1762368784822,"version":"build-2065373602"},"reference-count":44,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000183","name":"ARO","doi-asserted-by":"publisher","award":["W911NF1910269","W911NF2410094"],"award-info":[{"award-number":["W911NF1910269","W911NF2410094"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]},{"name":"DOE","award":["DE-SC0021417"],"award-info":[{"award-number":["DE-SC0021417"]}]},{"DOI":"10.13039\/501100004359","name":"Swedish Research Council","doi-asserted-by":"publisher","award":["2018-04359"],"award-info":[{"award-number":["2018-04359"]}],"id":[{"id":"10.13039\/501100004359","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000083","name":"NSF","doi-asserted-by":"publisher","award":["CCF-1817200","CCF-2008927","CCF-2200221","CCF-2311653","CCF-2148313","A22-2666-S003","DBI-2412522"],"award-info":[{"award-number":["CCF-1817200","CCF-2008927","CCF-2200221","CCF-2311653","CCF-2148313","A22-2666-S003","DBI-2412522"]}],"id":[{"id":"10.13039\/100000083","id-type":"DOI","asserted-by":"publisher"}]},{"name":"UCSD\/NSF","award":["KR 705319","A25-0139-S009"],"award-info":[{"award-number":["KR 705319","A25-0139-S009"]}]},{"DOI":"10.13039\/100000006","name":"ONR","doi-asserted-by":"publisher","award":["503400-78050","N00014-15-1-2550","N00014-22-1-2363"],"award-info":[{"award-number":["503400-78050","N00014-15-1-2550","N00014-22-1-2363"]}],"id":[{"id":"10.13039\/100000006","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.2025.3598253","type":"journal-article","created":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T17:36:28Z","timestamp":1755106588000},"page":"3843-3856","source":"Crossref","is-referenced-by-count":0,"title":["Coverage Analysis for Digital Cousin Selection \u2014 Improving Multi-Environment Q-Learning"],"prefix":"10.1109","volume":"73","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5178-8676","authenticated-orcid":false,"given":"Talha","family":"Bozkus","sequence":"first","affiliation":[{"name":"Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7112-1043","authenticated-orcid":false,"given":"Tara","family":"Javidi","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of California at San Diego, San Diego, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8896-1177","authenticated-orcid":false,"given":"Urbashi","family":"Mitra","sequence":"additional","affiliation":[{"name":"Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA"}]}],"member":"263","reference":[{"volume-title":"Reinforcement Learning: An Introduction","year":"2018","author":"Sutton","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF59524.2023.10476945"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2015.2420686"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"133653","DOI":"10.1109\/ACCESS.2019.2941229","volume":"7","author":"Jang","year":"2019","journal-title":"IEEE Access"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-statistics-031219-041220"},{"key":"ref6","article-title":"Double Q-learning","volume":"23","author":"Hasselt","year":"2010","journal-title":"Advances in Neural Inf. Process. Syst."},{"key":"ref7","first-page":"8454","article-title":"Ensemble bootstrapping for Q-learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Peer","year":"2021"},{"article-title":"Maxmin Q-learning: Controlling the estimation bias of Q-learning","year":"2020","author":"Lan","key":"ref8"},{"key":"ref9","first-page":"2411","article-title":"Speedy Q-learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"24","author":"Ghavamzadeh","year":"2011"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143955"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/11564096_32"},{"key":"ref12","first-page":"4033","article-title":"Deep exploration via bootstrapped DQN","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Osband","year":"2016"},{"article-title":"Playing Atari with deep reinforcement learning","year":"2013","author":"Mnih","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-72927-3_23"},{"key":"ref15","first-page":"2010","article-title":"Sample complexity of reinforcement learning using linearly combined model ensembles","volume-title":"Proc. Int. Nat. Conf. Artif. Intell. Statist.","author":"Modi","year":"2020"},{"article-title":"Model-ensemble trust-region policy optimization","year":"2018","author":"Kurutach","key":"ref16"},{"key":"ref17","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Chua","year":"2018"},{"key":"ref18","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih","year":"2016"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO55093.2022.9909958"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094828"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2024.3372699"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2024.3366434"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF59524.2023.10476963"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2023.3260562"},{"key":"ref25","first-page":"4863","article-title":"Is Q-learning provably efficient?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Jin","year":"2018"},{"key":"ref26","first-page":"7193","article-title":"Online robust reinforcement learning with model uncertainty","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Wang","year":"2021"},{"key":"ref27","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kumar","year":"2020"},{"key":"ref28","first-page":"104","article-title":"An optimistic perspective on offline reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Agarwal","year":"2020"},{"key":"ref29","first-page":"35300","article-title":"Leveraging offline data in online reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wagenmaker","year":"2023"},{"article-title":"Accelerating online reinforcement learning with offline datasets","year":"2020","author":"Nair","key":"ref30"},{"key":"ref31","first-page":"27395","article-title":"Policy finetuning: Bridging sample-efficient offline and online reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Xie","year":"2021"},{"article-title":"Hybrid RL: Using both offline and online data can make RL efficient","year":"2022","author":"Song","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2016.7849366"},{"article-title":"The role of coverage in online reinforcement learning","year":"2022","author":"Xie","key":"ref34"},{"article-title":"Pessimistic model-based offline reinforcement learning under partial coverage","year":"2021","author":"Uehara","key":"ref35"},{"key":"ref36","first-page":"22063","article-title":"What can online reinforcement learning with function approximation benefit from general coverage conditions?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu","year":"2023"},{"key":"ref37","first-page":"36599","article-title":"When to trust your simulator: Dynamics-aware hybrid offline-and-online reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Niu","year":"2022"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC60668.2024.10694661"},{"key":"ref39","first-page":"1","article-title":"Convergence of Q-learning: A simple proof","author":"Melo","year":"2001"},{"key":"ref40","first-page":"1","article-title":"Issues in using function approximation for reinforcement learning","volume-title":"Proc. Connectionist Models Summer School","volume":"6","author":"Thrun","year":"1993"},{"article-title":"Randomized ensembled double Q-learning: Learning fast without a model","year":"2021","author":"Chen","key":"ref41"},{"key":"ref42","first-page":"34978","article-title":"The virtues of laziness in model-based RL: A unified objective and algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Vemula","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890530"},{"article-title":"Generative multi-agent Q-learning for policy optimization: Decentralized wireless networks","year":"2025","author":"Bozkus","key":"ref44"}],"container-title":["IEEE Transactions on Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/78\/10807692\/11123709.pdf?arnumber=11123709","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:42:56Z","timestamp":1762368176000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11123709\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/tsp.2025.3598253","relation":{},"ISSN":["1053-587X","1941-0476"],"issn-type":[{"type":"print","value":"1053-587X"},{"type":"electronic","value":"1941-0476"}],"subject":[],"published":{"date-parts":[[2025]]}}}