{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T12:57:20Z","timestamp":1791464240813,"version":"4.3.4"},"reference-count":57,"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":[{"name":"University Synergy Innovation Program of Anhui Province","award":["GXXT-2022-040"],"award-info":[{"award-number":["GXXT-2022-040"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376085"],"award-info":[{"award-number":["62376085"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Provincial Natural Science Foundation of Anhui Higher Education Institution of China","award":["KJ2021A0040"],"award-info":[{"award-number":["KJ2021A0040"]}]},{"name":"Provincial Natural Science Foundation of Anhui Higher Education Institution of China","award":["KJ2021A0043"],"award-info":[{"award-number":["KJ2021A0043"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3543045","type":"journal-article","created":{"date-parts":[[2025,2,17]],"date-time":"2025-02-17T13:36:16Z","timestamp":1739799376000},"page":"5185-5197","source":"Crossref","is-referenced-by-count":4,"title":["Unbiased Meta Reinforcement Learning for Interactive Recommender Systems"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5521-0764","authenticated-orcid":false,"given":"Huiting","family":"Liu","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6196-1137","authenticated-orcid":false,"given":"Xinlong","family":"Lv","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1594-7187","authenticated-orcid":false,"given":"Peng","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9142-448X","authenticated-orcid":false,"given":"Peipei","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2396-1704","authenticated-orcid":false,"given":"Xindong","family":"Wu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Knowledge Engineering with Big Data, Ministry of Education of China, Hefei University of Technology, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2792838.2792840"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2020.2973141"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2505515.2505690"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401174"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013312"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16569"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3276505"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3089941"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3594871"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2978618"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2912124"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511963"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16601"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2839530"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330859"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403113"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403207"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570443"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20500-2_8"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539240"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583495"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401083"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/QRS-C55045.2021.00069"},{"key":"ref25","first-page":"267","article-title":"Collaborative filtering and the missing at random assumption","volume-title":"Proc. Uncertainty Artif. Intell.","author":"Marlin","year":"2007"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380255"},{"key":"ref27","first-page":"1670","article-title":"Recommendations as treatments: Debiasing learning and evaluation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schnabel","year":"2016"},{"key":"ref28","first-page":"3231","article-title":"The self-normalized estimator for counterfactual learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Swaminathan","year":"2015"},{"issue":"9","key":"ref29","first-page":"1265","article-title":"An MDP-based recommender system.","volume":"6","author":"Shani","year":"2005","journal-title":"J. Mach. Learn. Res."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401181"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591636"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3618107"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3209290"},{"key":"ref34","first-page":"2554","article-title":"Meta networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Munkhdalai","year":"2017"},{"key":"ref35","first-page":"1842","article-title":"Meta-learning with memory-augmented neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Santoro","year":"2016"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3460198"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109166"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3617827"},{"key":"ref41","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn","year":"2017"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614965"},{"issue":"1","key":"ref43","first-page":"3207","article-title":"Counterfactual reasoning and learning systems: The example of computational advertising","volume":"14","author":"Bottou","year":"2013","journal-title":"J. Mach. Learn. Res."},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/1835804.1835895"},{"key":"ref45","first-page":"6638","article-title":"Doubly robust joint learning for recommendation on data missing not at random","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2019"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614805"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s42486-024-00149-w"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3306618.3314288"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401431"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583856"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3088281"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3097186"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591656"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583361"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3126146"},{"key":"ref56","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018"},{"key":"ref57","first-page":"452","article-title":"BPR: Bayesian personalized ranking from implicit feedback","volume-title":"Proc. Conf. Uncertainty Artif. Intell.","author":"Rendle","year":"2009"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10891616.pdf?arnumber=10891616","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T04:24:43Z","timestamp":1756355083000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10891616\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3543045","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}