{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T20:52:52Z","timestamp":1775508772835,"version":"3.50.1"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"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":["62376275"],"award-info":[{"award-number":["62376275"]}],"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":["62472426"],"award-info":[{"award-number":["62472426"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Key Laboratory of Research on Large Models and Intelligent Governance"},{"name":"Engineering Research Center of Next-Generation Intelligent Search and Recommendation, MOE"},{"DOI":"10.13039\/501100004260","name":"Renmin University of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004260","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tpami.2026.3650796","type":"journal-article","created":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:38:31Z","timestamp":1767638311000},"page":"5655-5671","source":"Crossref","is-referenced-by-count":0,"title":["IBCB: Efficient Inverse Batched Contextual Bandit for Behavioral Evolution History"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2076-5374","authenticated-orcid":false,"given":"Yi","family":"Xu","sequence":"first","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4366-9276","authenticated-orcid":false,"given":"Weiran","family":"Shen","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7170-111X","authenticated-orcid":false,"given":"Jun","family":"Xu","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7397-5632","authenticated-orcid":false,"given":"Xiao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9777-9676","authenticated-orcid":false,"given":"Ji-Rong","family":"Wen","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198538677.003.0006"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/279943.279964"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3213246"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462892"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539393"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1989323.1989465"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052627"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113685"},{"key":"ref11","first-page":"10686","article-title":"Fairness of exposure in stochastic bandits","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2021"},{"key":"ref12","first-page":"2605","article-title":"Online learning with an unknown fairness metric","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gillen","year":"2018"},{"key":"ref13","first-page":"2586","article-title":"Bayesian inverse reinforcement learning","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Ramachandran","year":"2007"},{"key":"ref14","first-page":"1989","article-title":"Map inference for Bayesian inverse reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Choi","year":"2011"},{"key":"ref15","first-page":"9506","article-title":"Inverse contextual bandits: Learning how behavior evolves over time","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"H\u00fcy\u00fck","year":"2022"},{"key":"ref16","first-page":"1491","article-title":"One shot inverse reinforcement learning for stochastic linear bandits","volume-title":"Proc. 40th Conf. Uncertainty Artif. Intell.","author":"Guha","year":"2024"},{"key":"ref17","article-title":"Sequential batch learning in finite-action linear contextual bandits","author":"Han","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013445"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"key":"ref20","first-page":"424","article-title":"A contextual bandits framework for personalized learning action selection","volume-title":"Proc. 9th Int. Conf. Educ. Data Mining","author":"Lan","year":"2016"},{"key":"ref21","article-title":"Impact of representation learning in linear bandits","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Yang","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2023.4895"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3592474"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103500"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910371999"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2017.2676018"},{"key":"ref27","first-page":"6237","article-title":"An imitation learning approach for cache replacement","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu","year":"2020"},{"key":"ref28","first-page":"24","article-title":"On-policy robot imitation learning from a converging supervisor","volume-title":"Proc. Conf. Robot Learn.","author":"Balakrishna","year":"2020"},{"key":"ref29","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume-title":"Proc. Conf. Assoc. Advance. Artif. Intell.","author":"Ziebart","year":"2008"},{"key":"ref30","article-title":"Learning robust rewards with adverserial inverse reinforcement learning","volume-title":"Proc. 6th Int. Conf. Learn. Representations","author":"Fu","year":"2018"},{"key":"ref31","article-title":"Adversarial imitation via variational inverse reinforcement learning","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Qureshi","year":"2019"},{"key":"ref32","first-page":"4572","article-title":"Generative adversarial imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2016"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482347"},{"key":"ref34","article-title":"Deep Bayesian reward learning from preferences","volume-title":"Proc. Workshop Saf. Robustness Decis.-Mak. 33rd Conf. Neural Inf. Process. Syst.","author":"Brown","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3250269"},{"key":"ref36","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref38","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2019"},{"key":"ref39","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar","year":"2020"},{"key":"ref40","first-page":"5774","article-title":"Offline reinforcement learning with fisher divergence critic regularization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kostrikov","year":"2021"},{"key":"ref41","article-title":"Advantage-weighted regression: Simple and scalable off-policy reinforcement learning","author":"Peng","year":"2019"},{"key":"ref42","first-page":"18353","article-title":"BAIL: Best-action imitation learning for batch deep reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen","year":"2020"},{"key":"ref43","first-page":"21810","article-title":"MoReL: Model-based offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kidambi","year":"2020"},{"key":"ref44","first-page":"28954","article-title":"COMBO: Conservative offline model-based policy optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-3216-0_8"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2013.6669541"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/641876.641880"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s12532-014-0071-1"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s12532-020-00179-2"},{"key":"ref50","article-title":"Exposure-aware recommendation using contextual bandits","author":"Mansoury","year":"2022"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"ref52","first-page":"22596","article-title":"AdaO2B: Adaptive online to batch conversion for out-of-distribution generalization","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Zhang","year":"2025"},{"key":"ref53","article-title":"Deep graph library: A graph-centric, highly-performant package for graph neural networks","author":"Wang","year":"2019"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/S0016-0032(96)00063-4"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11474534\/11328925.pdf?arnumber=11328925","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T19:56:17Z","timestamp":1775505377000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11328925\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":55,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3650796","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}