{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T15:26:27Z","timestamp":1777994787773,"version":"3.51.4"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"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":["62076096"],"award-info":[{"award-number":["62076096"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"crossref","award":["22ZR1421700"],"award-info":[{"award-number":["22ZR1421700"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Shanghai Knowledge Service Platform","award":["ZF1213"],"award-info":[{"award-number":["ZF1213"]}]},{"name":"Open Research Fund of Key Laboratory of Advanced Theory and Application in Statistics and Data Science-Ministry of Education"},{"DOI":"10.13039\/501100001809","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tnnls.2024.3443082","type":"journal-article","created":{"date-parts":[[2024,8,23]],"date-time":"2024-08-23T13:56:00Z","timestamp":1724421360000},"page":"12655-12667","source":"Crossref","is-referenced-by-count":3,"title":["De-Pessimism Offline Reinforcement Learning via Value Compensation"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7772-921X","authenticated-orcid":false,"given":"Zhenbo","family":"Huang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0158-5330","authenticated-orcid":false,"given":"Jing","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7069-3752","authenticated-orcid":false,"given":"Shiliang","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101834"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2773458"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084685"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20894"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10827"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3095161"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3025711"},{"key":"ref8","first-page":"1","article-title":"Stabilizing off-policy Q-learning via bootstrapping error reduction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Kumar"},{"key":"ref9","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Fujimoto"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3082568"},{"key":"ref11","article-title":"AWAC: Accelerating online reinforcement learning with offline datasets","author":"Nair","year":"2020","journal-title":"arXiv:2006.09359"},{"key":"ref12","first-page":"11319","article-title":"Uncertainty weighted actor-critic for offline reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu"},{"key":"ref13","first-page":"22233","article-title":"Dropout reduces underfitting","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"202","author":"Liu"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3250269"},{"key":"ref15","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kumar"},{"key":"ref16","first-page":"1711","article-title":"Mildly conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Lyu"},{"key":"ref17","first-page":"1","article-title":"Supported trust region optimization for offline reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"141","author":"Mao"},{"key":"ref18","first-page":"1","article-title":"Offline reinforcement learning with implicit Q-learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kostrikov"},{"key":"ref19","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref20","article-title":"Quantile filtered imitation learning","author":"Brandfonbrener","year":"2021","journal-title":"arXiv:2112.00950"},{"key":"ref21","first-page":"18353","article-title":"BAIL: Best-action imitation learning for batch deep reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Chen"},{"key":"ref22","article-title":"Advantage-weighted regression: Simple and scalable off-policy reinforcement learning","author":"Peng","year":"2019","journal-title":"arXiv:1910.00177"},{"key":"ref23","first-page":"7768","article-title":"Critic regularized regression","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Wang"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3142822"},{"key":"ref25","first-page":"759","article-title":"Eligibility traces for off-policy policy evaluation","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Precup"},{"key":"ref26","article-title":"Behavior regularized offline reinforcement learning","author":"Wu","year":"2019","journal-title":"arXiv:1911.11361"},{"key":"ref27","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Fujimoto"},{"key":"ref28","first-page":"5774","article-title":"Offline reinforcement learning with Fisher divergence critic regularization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kostrikov"},{"key":"ref29","first-page":"1006","article-title":"Error bounds for approximate value iteration","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"19","author":"Munos"},{"key":"ref30","first-page":"28954","article-title":"COMBO: Conservative offline model-based policy optimization","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Yu"},{"key":"ref31","first-page":"19235","article-title":"Conservative offline distributional reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Ma"},{"key":"ref32","first-page":"6683","article-title":"Bellman-consistent pessimism for offline reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Xie"},{"key":"ref33","volume-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1515\/9781400835386"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref36","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Achiam"},{"key":"ref37","first-page":"267","article-title":"Approximately optimal approximate reinforcement learning","volume-title":"Proc. 19th Int. Conf. Mach. Learn.","author":"Kakade"},{"key":"ref38","first-page":"2859","article-title":"Learning from limited demonstrations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Kim"},{"key":"ref39","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Sohn"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref41","first-page":"1","article-title":"Reining generalization in offline reinforcement learning via representation distinction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Ma"},{"key":"ref42","first-page":"1455","article-title":"Dealing with the unknown: Pessimistic offline reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Li"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.049"},{"key":"ref44","article-title":"D4RL: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020","journal-title":"arXiv:2004.07219"},{"key":"ref45","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen"},{"key":"ref46","first-page":"14129","article-title":"MOPO: Model-based offline policy optimization","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Yu"},{"key":"ref47","first-page":"21810","article-title":"MOReL: Model-based offline reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kidambi"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11073756\/10645715.pdf?arnumber=10645715","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:39:43Z","timestamp":1764959983000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10645715\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":47,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3443082","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}