{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T16:23:32Z","timestamp":1781972612491,"version":"3.54.5"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2023YFC2415100"],"award-info":[{"award-number":["2023YFC2415100"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222316"],"award-info":[{"award-number":["62222316"]}],"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":["62373351"],"award-info":[{"award-number":["62373351"]}],"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":["82327801"],"award-info":[{"award-number":["82327801"]}],"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":["62073325"],"award-info":[{"award-number":["62073325"]}],"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":["62303463"],"award-info":[{"award-number":["62303463"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Chinese Academy of Sciences Project for Young Scientists in Basic Research","award":["YSBR-104"],"award-info":[{"award-number":["YSBR-104"]}]},{"name":"Beijing Natural Science Foundation","award":["F252068"],"award-info":[{"award-number":["F252068"]}]},{"name":"Beijing Natural Science Foundation","award":["4254107"],"award-info":[{"award-number":["4254107"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2024M763535"],"award-info":[{"award-number":["2024M763535"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CAMS Innovation Fund for Medical Sciences","award":["2023-I2M-C&T-B-017"],"award-info":[{"award-number":["2023-I2M-C&T-B-017"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tsmc.2025.3578666","type":"journal-article","created":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T13:39:08Z","timestamp":1751981948000},"page":"7142-7155","source":"Crossref","is-referenced-by-count":2,"title":["DOMAIN: Mildly Conservative Model-Based Offline Reinforcement Learning"],"prefix":"10.1109","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7407-2216","authenticated-orcid":false,"given":"Xiao-Yin","family":"Liu","sequence":"first","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7602-4848","authenticated-orcid":false,"given":"Xiao-Hu","family":"Zhou","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mei-Jiang","family":"Gui","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9201-2700","authenticated-orcid":false,"given":"Guo-Tao","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6227-4811","authenticated-orcid":false,"given":"Xiao-Liang","family":"Xie","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1790-8448","authenticated-orcid":false,"given":"Shi-Qi","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4316-3259","authenticated-orcid":false,"given":"Shuang-Yi","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi-Chao","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3353-2586","authenticated-orcid":false,"given":"Biao","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Automation, Central South University, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1534-5840","authenticated-orcid":false,"given":"Zeng-Guang","family":"Hou","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"651","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","volume-title":"Proc. 2nd Conf. Robot Learn.","author":"Kalashnikov"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.birob.2022.100047"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2023.3310021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMRB.2024.3407349"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.34133\/cbsystems.0089"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.birob.2022.100066"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342080"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3150802"},{"key":"ref10","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020","journal-title":"arXiv:2005.01643"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3250269"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3443082"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2024.3388007"},{"key":"ref14","first-page":"23851","article-title":"RORL: Robust offline reinforcement learning via conservative smoothing","volume-title":"Proc. 36th Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref15","first-page":"21024","article-title":"Robust deep reinforcement learning against adversarial perturbations on state observations","volume-title":"Proc. 34th Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref16","first-page":"11784","article-title":"Stabilizing off-policy Q-learning via bootstrapping error reduction","volume-title":"Proc. 33rd Conf. Neural Inf. Process. Syst.","author":"Kumar"},{"key":"ref17","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref18","article-title":"Behavior regularized offline reinforcement learning","author":"Wu","year":"2019","journal-title":"arXiv:1911.11361"},{"key":"ref19","first-page":"204","article-title":"BRAC+: Improved behavior regularized actor critic for offline reinforcement learning","volume-title":"Proc. Asian Conf. Mach. Learn.","author":"Zhang"},{"key":"ref20","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. 34th Conf. Neural Inf. Process. Syst.","author":"Kumar"},{"key":"ref21","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst.","author":"Fujimoto"},{"key":"ref22","first-page":"1711","article-title":"Mildly conservative Q-learning for offline reinforcement learning","volume-title":"Proc. 36th Conf. Neural Inf. Process. Syst.","author":"Lyu"},{"key":"ref23","first-page":"1","article-title":"Model based reinforcement learning for Atari","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kaiser"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-022-3696-5"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2958912"},{"key":"ref26","first-page":"14129","article-title":"MOPO: Model-based offline policy optimization","volume-title":"Proc. 34th Conf. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref27","first-page":"21810","article-title":"MOReL: Model-based offline reinforcement learning","volume-title":"Proc. 34th Conf. Neural Inf. Process. Syst.","author":"Kidambi"},{"key":"ref28","first-page":"28954","article-title":"COMBO: Conservative offline model-based policy optimization","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3309906"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3293508"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3317131"},{"key":"ref32","first-page":"29420","article-title":"Offline reinforcement learning with reverse model-based imagination","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref33","first-page":"18353","article-title":"BAIL: Best-action imitation learning for batch deep reinforcement learning","volume-title":"Proc. 34th Conf. Neural Inf. Process. Syst.","author":"Chen"},{"issue":"1","key":"ref34","first-page":"1395","article-title":"A review of robot learning for manipulation: Challenges, representations, and algorithms","volume":"22","author":"Kroemer","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref35","first-page":"12519","article-title":"When to trust your model: Model-based policy optimization","volume-title":"Proc. 33rd Conf. Neural Inf. Process. Syst.","author":"Janner"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.2307\/jj.20206644.79"},{"key":"ref37","first-page":"1245","article-title":"Adversarial model for offline reinforcement learning","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Bhardwaj"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2024.3372939"},{"issue":"200","key":"ref39","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":"ref40","first-page":"4587","article-title":"MICRO: Model-based offline reinforcement learning with a conservative bellman operator","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Liu"},{"key":"ref41","first-page":"1057","article-title":"Policy gradient method for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutton"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref43","first-page":"36599","article-title":"When to trust your simulator: Dynamics-aware hybrid offline-and-online reinforcement learning","volume-title":"Proc. 36th Conf. Neural Inf. Process. Syst.","author":"Niu"},{"key":"ref44","article-title":"CROP: Conservative reward for model-based offline policy optimization","author":"Li","year":"2023","journal-title":"arXiv:2310.17245"},{"key":"ref45","article-title":"Off-dynamics reinforcement learning: Training for transfer with domain classifiers","author":"Eysenbach","year":"2020","journal-title":"arXiv:2006.13916"},{"key":"ref46","first-page":"1455","article-title":"Dealing with the unknown: Pessimistic offline reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Li"},{"key":"ref47","first-page":"3652","article-title":"Safe policy improvement with baseline bootstrapping","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Laroche"},{"key":"ref48","first-page":"2306","article-title":"Safe policy improvement by minimizing robust baseline regret","volume-title":"Proc. 30th Conf. Neural Inf. Process. Syst.","author":"Ghavamzadeh"},{"key":"ref49","first-page":"2701","article-title":"Why is posterior sampling better than optimism for reinforcement learning?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Osband"},{"key":"ref50","article-title":"OpenAI gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref51","article-title":"D4RL: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020","journal-title":"arXiv:2004.07219"},{"key":"ref52","first-page":"1","article-title":"Offline reinforcement learning with implicit Q-learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kostrikov"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221021\/11173422\/11072806.pdf?arnumber=11072806","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T13:51:40Z","timestamp":1759240300000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11072806\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":53,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2025.3578666","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"value":"2168-2216","type":"print"},{"value":"2168-2232","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}