{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T20:06:38Z","timestamp":1780603598063,"version":"3.54.1"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"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":["62506157"],"award-info":[{"award-number":["62506157"]}],"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":["62276128"],"award-info":[{"award-number":["62276128"]}],"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":["62192783"],"award-info":[{"award-number":["62192783"]}],"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":["62206133"],"award-info":[{"award-number":["62206133"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jiangsu Science and Technology Major Project","award":["BG2024031"],"award-info":[{"award-number":["BG2024031"]}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"crossref","award":["BK20243051"],"award-info":[{"award-number":["BK20243051"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["14380128"],"award-info":[{"award-number":["14380128"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100017085","name":"Collaborative Innovation Center of Novel Software Technology and Industrialization","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017085","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":[[2026,6]]},"DOI":"10.1109\/tnnls.2025.3636176","type":"journal-article","created":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T18:49:00Z","timestamp":1764701340000},"page":"2592-2606","source":"Crossref","is-referenced-by-count":0,"title":["Model-Based Offline Reinforcement Learning With Adversarial Data Augmentation"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2537-2295","authenticated-orcid":false,"given":"Hongye","family":"Cao","sequence":"first","affiliation":[{"name":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3043-2360","authenticated-orcid":false,"given":"Fan","family":"Feng","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, City University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8504-455X","authenticated-orcid":false,"given":"Jing","family":"Huo","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5379-9539","authenticated-orcid":false,"given":"Shangdong","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6745-286X","authenticated-orcid":false,"given":"Meng","family":"Fang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Liverpool, Liverpool, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5497-7146","authenticated-orcid":false,"given":"Tianpei","family":"Yang","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2488-1813","authenticated-orcid":false,"given":"Yang","family":"Gao","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3497667"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3109284"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3280161"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3477600"},{"key":"ref6","article-title":"Stabilizing off-policy Q-learning via bootstrapping error reduction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar"},{"key":"ref7","article-title":"Boosting offline reinforcement learning for autonomous driving with hierarchical latent skills","author":"Li","year":"2023","journal-title":"arXiv:2309.13614"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3293508"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3328397"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3443082"},{"key":"ref11","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3488358"},{"key":"ref13","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":"ref14","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"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3317131"},{"key":"ref16","first-page":"449","article-title":"Model-based offline reinforcement learning with pessimism-modulated dynamics belief","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Guo"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.2307\/jj.20206644.79"},{"key":"ref18","article-title":"CROP: Conservative reward for model-based offline policy optimization","author":"Li","year":"2023","journal-title":"arXiv:2310.17245"},{"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":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020","journal-title":"arXiv:2005.01643"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.65109\/rxjw7650"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1789"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/iros58592.2024.10802094"},{"key":"ref24","first-page":"2817","article-title":"Robust adversarial reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pinto"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2020.3028078"},{"key":"ref26","first-page":"26156","article-title":"Robust deep reinforcement learning through adversarial loss","volume-title":"Proc. 35th Int. Conf. Neural Inf. Process. Syst.","author":"Oikarinen"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i5.20481"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0060"},{"key":"ref29","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":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/iros.2012.6386109"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1137\/s0363012996299557"},{"key":"ref32","first-page":"1321","article-title":"Approximate dynamic programming for two-player zero-sum Markov games","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"P\u00e9rolat"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176345637"},{"key":"ref34","volume-title":"Early Fixed Point Theorems","year":"1980"},{"key":"ref35","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bellemare"},{"key":"ref36","article-title":"D4RL: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020","journal-title":"arXiv:2004.07219"},{"key":"ref37","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018","journal-title":"arXiv:1801.01290"},{"key":"ref38","first-page":"1","article-title":"Pessimistic bootstrapping for uncertainty-driven offline reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Bai"},{"key":"ref39","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":"ref40","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/514"},{"key":"ref41","first-page":"7436","article-title":"Uncertainty-based offline reinforcement learning with diversified Q-ensemble","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"An"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.65109\/ckda9676"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29607"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11549955\/11271829.pdf?arnumber=11271829","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T19:56:31Z","timestamp":1780602991000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11271829\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":43,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3636176","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}