{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T14:47:29Z","timestamp":1773931649934,"version":"3.50.1"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2022ZD0119901"],"award-info":[{"award-number":["2022ZD0119901"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U2141234"],"award-info":[{"award-number":["U2141234"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Science and Technology Program","award":["22015810300"],"award-info":[{"award-number":["22015810300"]}]},{"name":"Hainan Province Science and Technology Special Fund","award":["ZDYF2024GXJS003"],"award-info":[{"award-number":["ZDYF2024GXJS003"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1109\/tcyb.2024.3385910","type":"journal-article","created":{"date-parts":[[2024,4,26]],"date-time":"2024-04-26T17:39:50Z","timestamp":1714153190000},"page":"3692-3704","source":"Crossref","is-referenced-by-count":11,"title":["Offline Reinforcement Learning With Behavior Value Regularization"],"prefix":"10.1109","volume":"54","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5123-5043","authenticated-orcid":false,"given":"Longyang","family":"Huang","sequence":"first","affiliation":[{"name":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2026-6856","authenticated-orcid":false,"given":"Botao","family":"Dong","sequence":"additional","affiliation":[{"name":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4984-6659","authenticated-orcid":false,"given":"Wei","family":"Xie","sequence":"additional","affiliation":[{"name":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4700-1276","authenticated-orcid":false,"given":"Weidong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3199213"},{"key":"ref3","first-page":"10178","article-title":"Oracle-free reinforcement learning in mean-field games along a single sample path","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Zaman"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3178819"},{"key":"ref5","first-page":"12287","article-title":"Exponential lower bounds for batch reinforcement learning: Batch RL can be exponentially harder than online RL","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zanette"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3053414"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tg.2022.3224088"},{"key":"ref8","article-title":"Behavioral priors and dynamics models: Improving performance and domain transfer in offline RL","author":"Cang","year":"2021","journal-title":"arXiv:2106.09119"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tii.2023.3333921"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2949596"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_2"},{"key":"ref12","article-title":"Offline reinforcement learning: tutorial, review, and perspectives on open problems","author":"Levine","year":"2020","journal-title":"arXiv:2005.01643"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3309906"},{"key":"ref14","first-page":"1774","article-title":"Hallucinated adversarial control for conservative offline policy evaluation","volume-title":"Proc. Uncertain. Artif. Intell.","author":"Rothfuss"},{"key":"ref15","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proce. Adv. Neural Inf. Process. Syst.","author":"Kumar"},{"key":"ref16","first-page":"1582","article-title":"Addressing function approximation error in actor\u2013critic methods","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3015811"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3157892"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3104612"},{"key":"ref20","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref21","first-page":"21810","article-title":"MOReL: Model-based offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kidambi"},{"key":"ref22","first-page":"14129","article-title":"MOPO: Model-based offline policy optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2021.104366"},{"key":"ref24","first-page":"3682","article-title":"EMaQ: Expected-max-learning operator for simple yet effective offline and online RL","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ghasemipour"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tcds.2023.3287987"},{"key":"ref26","article-title":"Behavior regularized offline reinforcement learning","author":"Wu","year":"2019","journal-title":"arXiv:1911.11361"},{"key":"ref27","first-page":"1","article-title":"Batch reinforcement learning through continuation method","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Guo"},{"key":"ref28","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fujimoto"},{"key":"ref29","first-page":"1","article-title":"When data geometry meets deep function: Generalizing offline reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26130"},{"key":"ref31","first-page":"7768","article-title":"Critic regularized regression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref32","first-page":"1","article-title":"Offline reinforcement learning with implicit Q-learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kostrikov"},{"key":"ref33","article-title":"Regularized behavior value estimation","author":"Gulcehre","year":"2021","journal-title":"arXiv:2103.09575"},{"key":"ref34","article-title":"DCE: Offline reinforcement learning with double conservative estimates","author":"Zhao","year":"2022","journal-title":"arXiv: 2209.13132"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3364844"},{"key":"ref36","first-page":"33177","article-title":"Model-Bellman inconsistency for model-based offline reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sun"},{"key":"ref37","article-title":"DOMAIN: Mildly conservative model-based offline reinforcement learning","author":"Liu","year":"2023","journal-title":"arXiv:2309.08925"},{"key":"ref38","first-page":"51881","article-title":"Conservative offline policy adaptation in multi-agent games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref39","first-page":"77290","article-title":"Counterfactual conservative Q learning for offline multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Shao"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20855"},{"key":"ref41","first-page":"33758","article-title":"VOCE: Variational optimization with conservative estimation for offline safe reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Guan"},{"key":"ref42","article-title":"D4RL: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020","journal-title":"arXiv:2004.07219"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/10542154\/10509017.pdf?arnumber=10509017","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T18:56:04Z","timestamp":1732906564000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10509017\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":42,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2024.3385910","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6]]}}}