{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T21:54:17Z","timestamp":1772574857438,"version":"3.50.1"},"reference-count":59,"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":["62220106008"],"award-info":[{"award-number":["62220106008"]}],"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.2025.3615982","type":"journal-article","created":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:54:25Z","timestamp":1760032465000},"page":"1362-1376","source":"Crossref","is-referenced-by-count":0,"title":["Inhibiting Error Exacerbation in Offline Reinforcement Learning With Data Sparsity"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5894-3237","authenticated-orcid":false,"given":"Fan","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2345-0974","authenticated-orcid":false,"given":"Malu","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9933-8014","authenticated-orcid":false,"given":"Wenyu","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3180-0815","authenticated-orcid":false,"given":"Siying","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5893-6563","authenticated-orcid":false,"given":"Xin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Mechanical and Aerospace Engineering, The Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3741-5055","authenticated-orcid":false,"given":"Jiayin","family":"Li","sequence":"additional","affiliation":[{"name":"Xiamen University Malaysia, Selangor, Malaysia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5070-4511","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Maxmin Q-learning: Controlling the estimation bias of Q-learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lan"},{"key":"ref2","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":"ref3","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3059912"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2890974"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2949596"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3107202"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3103132"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2932203"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3157198"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3133717"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3057424"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3190471"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3142822"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3116063"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0310-5"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"},{"key":"ref18","article-title":"A review of safe reinforcement learning: Methods, theory and applications","author":"Gu","year":"2022","journal-title":"arXiv:2205.10330"},{"key":"ref19","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":"ref20","article-title":"D4RL: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020","journal-title":"arXiv:2004.07219"},{"key":"ref21","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kumar"},{"key":"ref22","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":"ref23","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref24","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020","journal-title":"arXiv:2005.01643"},{"key":"ref25","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Fujimoto"},{"key":"ref26","article-title":"Behavior regularized offline reinforcement learning","author":"Wu","year":"2019","journal-title":"arXiv:1911.11361"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747886"},{"key":"ref28","article-title":"AWAC: Accelerating online reinforcement learning with offline datasets","author":"Nair","year":"2020","journal-title":"arXiv:2006.09359"},{"key":"ref29","article-title":"Advantage-weighted regression: Simple and scalable off-policy reinforcement learning","author":"Bin Peng","year":"2019","journal-title":"arXiv:1910.00177"},{"key":"ref30","first-page":"7768","article-title":"Critic regularized regression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Wang"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3453385"},{"key":"ref32","first-page":"27395","article-title":"Policy finetuning: Bridging sample-efficient offline and online reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Xie"},{"key":"ref33","first-page":"6683","article-title":"Bellman-consistent pessimism for offline reinforcement learning","volume":"34","author":"Xie","year":"2021","journal-title":"Adv. neural Inf. Process. Syst."},{"key":"ref34","article-title":"Uncertainty weighted actor-critic for offline reinforcement learning","author":"Wu","year":"2021","journal-title":"arXiv:2105.08140"},{"key":"ref35","first-page":"1","article-title":"When to trust your model: Model-based policy optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Janner"},{"key":"ref36","first-page":"21810","article-title":"MOReL: Model-based offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kidambi"},{"key":"ref37","first-page":"14129","article-title":"MOPO: Model-based offline policy optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Yu"},{"key":"ref38","first-page":"4085","article-title":"A policy-guided imitation approach for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Xu"},{"key":"ref39","article-title":"Rethinking goal-conditioned supervised learning and its connection to offline RL","author":"Yang","year":"2022","journal-title":"arXiv:2202.04478"},{"key":"ref40","first-page":"6266","article-title":"Curriculum offline imitating learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Liu"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3672059"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/tit.2022.3185139"},{"key":"ref43","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1629"},{"key":"ref45","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref47","first-page":"767","article-title":"Interference and generalization in temporal difference learning","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"1","author":"Bengio"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2795041"},{"key":"ref49","volume-title":"Foundations of Machine Learning","author":"Mohri","year":"2018"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2024.3384509"},{"key":"ref51","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref52","article-title":"NeoRL-2: Near real-world benchmarks for offline reinforcement learning with extended realistic scenarios","author":"Gao","year":"2025","journal-title":"arXiv:2503.19267"},{"key":"ref53","first-page":"1","article-title":"Offline reinforcement learning with implicit Q-learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kostrikov"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3293508"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3488358"},{"key":"ref56","article-title":"Offline reinforcement learning with OOD state correction and OOD action suppression","author":"Mao","year":"2024","journal-title":"arXiv:2410.19400"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.02.039"},{"key":"ref58","first-page":"3703","article-title":"Batch policy learning under constraints","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Le"},{"issue":"27","key":"ref59","first-page":"815","article-title":"Finite-time bounds for fitted value iteration","volume":"9","author":"Munos","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11418705\/11197576.pdf?arnumber=11197576","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T20:53:22Z","timestamp":1772571202000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11197576\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":59,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3615982","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}