{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T12:02:03Z","timestamp":1792756923305,"version":"4.5.0"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176259,62373364"],"award-info":[{"award-number":["62176259,62373364"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/CAA J. Autom. Sinica"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/jas.2024.124494","type":"journal-article","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T19:08:57Z","timestamp":1732129737000},"page":"2497-2511","source":"Crossref","is-referenced-by-count":4,"title":["Robust Offline Actor-Critic with On-Policy Regularized Policy Evaluation"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3998-461X","authenticated-orcid":false,"given":"Shuo","family":"Cao","sequence":"first","affiliation":[{"name":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education,Xuzhou,China,221116"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5327-1088","authenticated-orcid":false,"given":"Xuesong","family":"Wang","sequence":"additional","affiliation":[{"name":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education,Xuzhou,China,221116"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0636-5820","authenticated-orcid":false,"given":"Yuhu","family":"Cheng","sequence":"additional","affiliation":[{"name":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education,Xuzhou,China,221116"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3155483"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123843"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2022.105506"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2023.3274908"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3051456"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2021.1004258"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3237580"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3098985"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123186"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26130"},{"key":"ref12","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_2"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3250269"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3288050"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3202185"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2021.1004395"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2023.3271900"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3050619"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2023.3298807"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123558"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3203074"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3088063"},{"key":"ref24","article-title":"In-sample policy iteration for offline reinforcement learning","author":"Hu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2019"},{"key":"ref26","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Fujimoto","year":"2021"},{"key":"ref27","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kumar","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3309906"},{"key":"ref29","article-title":"Offline reinforcement learning with implicit Q-learning","author":"Kostrikov","year":"2021","journal-title":"arXiv preprint"},{"key":"ref30","first-page":"11784","article-title":"Stabilizing off-policy Q-learning via bootstrapping error reduction","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kumar","year":"2019"},{"key":"ref31","article-title":"Behavior regularized offline reinforcement learning","author":"Wu","year":"2019","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/687"},{"key":"ref33","article-title":"Accelerating online reinforcement learning with offline datasets","author":"Nair","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Density estimation for conservative Q-learning","volume-title":"Proc. ICLR Workshop Generalizable Policy Learning in Physical World","author":"Daoudi","year":"2022"},{"key":"ref35","first-page":"1711","article-title":"Mildly conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lyu","year":"2022"},{"key":"ref36","article-title":"Uncertainty weighted Actor-Critic for offline reinforcement learning","author":"Wu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Pessimistic bootstrapping for uncertainty-driven offline reinforcement learning","author":"Bai","year":"2022","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Offline RL with no OOD actions: In-sample learning via implicit value regularization","author":"Xu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"The in-sample softmax for offline reinforcement learning","author":"Xiao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref40","first-page":"4933","article-title":"Offline rl without off-policy evaluation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Brandfonbrener","year":"2021"},{"key":"ref41","article-title":"Behavior proximal policy optimization","author":"Zhuang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43421-1_27"},{"key":"ref43","article-title":"D4RL: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref45","first-page":"568","article-title":"Error propagation for approximate policy and value iteration","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Farahmand","year":"2010"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3364844"},{"key":"ref47","first-page":"4666","article-title":"Guarantees for epsilon-greedy reinforcement learning with function approximation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dann","year":"2022"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3096966"},{"key":"ref49","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2018"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553495"}],"container-title":["IEEE\/CAA Journal of Automatica Sinica"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570654\/10759594\/10759596.pdf?arnumber=10759596","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T18:20:30Z","timestamp":1732731630000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10759596\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":50,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/jas.2024.124494","relation":{},"ISSN":["2329-9266","2329-9274"],"issn-type":[{"value":"2329-9266","type":"print"},{"value":"2329-9274","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}