{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T21:54:18Z","timestamp":1772574858852,"version":"3.50.1"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"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":["62476128"],"award-info":[{"award-number":["62476128"]}],"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":[[2026,3]]},"DOI":"10.1109\/tnnls.2025.3616159","type":"journal-article","created":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T17:40:51Z","timestamp":1760463651000},"page":"1347-1361","source":"Crossref","is-referenced-by-count":0,"title":["Toward Reliable Offline Reinforcement Learning via Lyapunov Uncertainty Control"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3113-3786","authenticated-orcid":false,"given":"Ke","family":"Jiang","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, MIIT Key Laboratory of Pattern Analysis and Machine Intelligence, Nanjing University of Aeronautics and Astronautics, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6356-7926","authenticated-orcid":false,"given":"Yao","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer and Information Technology, Shanxi University, Taiyuan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2683-8667","authenticated-orcid":false,"given":"Xiaoyang","family":"Tan","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, MIIT Key Laboratory of Pattern Analysis and Machine Intelligence, Nanjing University of Aeronautics and Astronautics, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2","article-title":"Model selection for offline reinforcement learning: Practical considerations for healthcare settings","volume-title":"Proc. 6th Mach. Learn. Healthcare Conf.","author":"Tang"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2021.3054625"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/robotics10030105"},{"key":"ref4","first-page":"10708","article-title":"Lyapunov density models: Constraining distribution shift in learning-based control","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"162","author":"Kang"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1685"},{"key":"ref6","first-page":"14129","article-title":"MOPO: Model-based offline policy optimization","volume-title":"Proc. 33rd Adv. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref7","first-page":"4425","article-title":"Pessimistic bootstrapping for uncertainty-driven offline reinforcement learning","volume-title":"Proc. 10th Int. Conf. Learn. Represent.","author":"Bai"},{"key":"ref8","article-title":"RORL: Robust offline reinforcement learning via conservative smoothing","author":"Yang","year":"2022","journal-title":"arXiv:2206.02829"},{"key":"ref9","first-page":"32211","article-title":"Robust reinforcement learning using offline data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Panaganti"},{"issue":"200","key":"ref10","first-page":"1","article-title":"Distributionally robust model-based offline reinforcement learning with near-optimal sample complexity","volume":"25","author":"Shi","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref11","article-title":"Robust constraint satisfaction: Invariant sets and predictive control","author":"Kerrigan","year":"2000"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2017.xiii.064"},{"key":"ref13","first-page":"11761","article-title":"Stabilizing off-policy Q-learning via bootstrapping error reduction","volume-title":"Proc. 32nd Adv. Neural Inf. Process. Syst.","author":"Kumar"},{"key":"ref14","article-title":"Behavior regularized offline reinforcement learning","author":"Wu","year":"2019","journal-title":"arXiv:1911.11361"},{"key":"ref15","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. 33rd Adv. Neural Inf. Process. Syst.","author":"Kumar"},{"key":"ref16","first-page":"20876","article-title":"Offline reinforcement learning with implicit Q-learning","volume-title":"Proc. 10th Int. Conf. Learn. Represent.","author":"Kostrikov"},{"key":"ref17","first-page":"31278","article-title":"Supported policy optimization for offline reinforcement learning","volume-title":"Proc. 35thAdv. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref18","first-page":"40587","article-title":"Supported value regularization for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Mao"},{"key":"ref19","first-page":"7436","article-title":"Uncertainty-based offline reinforcement learning with diversified Q-ensemble","volume-title":"Proc. 34th Adv. Neural Inf. Process. Syst.","author":"An"},{"key":"ref20","first-page":"33177","article-title":"Model-bellman inconsistency for model-based offline reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sun"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3497667"},{"key":"ref22","first-page":"9022","article-title":"State deviation correction for offline reinforcement learning","volume-title":"Proc. 36th AAAI Conf. Artif. Intell.","volume":"36","author":"Zhang"},{"key":"ref23","article-title":"Offline reinforcement learning with OOD state correction and OOD action suppression","author":"Mao","year":"2024","journal-title":"arXiv:2410.19400"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/bf00992698"},{"key":"ref25","first-page":"5084","article-title":"Is pessimism provably efficient for offline RL","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Jin"},{"key":"ref26","first-page":"143","article-title":"DART: Noise injection for robust imitation learning","volume-title":"Proc. 1st Annu. Conf. Robot Learn.","author":"Laskey"},{"key":"ref27","article-title":"D4RL: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020","journal-title":"arXiv:2004.07219"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3217189"},{"key":"ref30","first-page":"3852","article-title":"Adversarially trained actor critic for offline reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cheng"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3737257"},{"key":"ref32","first-page":"24753","article-title":"NeoRL: A near real-world benchmark for offline reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Qin"},{"key":"ref33","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":"ref34","first-page":"1","article-title":"Error bounds for approximate value iteration","volume-title":"Proc. Nat. Conf. Artif. Intell.","volume":"20","author":"Munos"},{"key":"ref35","first-page":"2298","article-title":"Safe policy improvement by minimizing robust baseline regret","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Petrik"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11418705\/11203256.pdf?arnumber=11203256","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T20:53:23Z","timestamp":1772571203000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11203256\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":35,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3616159","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}