{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T16:23:53Z","timestamp":1783873433003,"version":"3.55.0"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"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":["62176259"],"award-info":[{"award-number":["62176259"]}],"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":["62373364"],"award-info":[{"award-number":["62373364"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Program of Jiangsu Province","award":["BE2022095"],"award-info":[{"award-number":["BE2022095"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1109\/tsmc.2024.3388007","type":"journal-article","created":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T17:31:04Z","timestamp":1714584664000},"page":"4841-4852","source":"Crossref","is-referenced-by-count":8,"title":["Dual Behavior Regularized Offline Deterministic Actor\u2013Critic"],"prefix":"10.1109","volume":"54","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, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"}],"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, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2022-9999","authenticated-orcid":false,"given":"Yuhu","family":"Cheng","sequence":"additional","affiliation":[{"name":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, 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.2022.3186229"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2023.3274908"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3270444"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3098451"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3093905"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3098985"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3213566"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2931946"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2020.2966631"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2019.2955905"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3211622"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSTE.2022.3148236"},{"key":"ref14","article-title":"Conservative state value estimation for offline reinforcement learning","author":"Chen","year":"2023","journal-title":"arXiv:2302.06884"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_2"},{"key":"ref16","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020","journal-title":"arXiv:2005.01643"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20783"},{"key":"ref18","article-title":"D4RL: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020","journal-title":"arXiv:2004.07219"},{"key":"ref19","first-page":"2307","article-title":"Offline reinforcement learning with pseudometric learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dadashi"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3250269"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2024.3385910"},{"key":"ref22","article-title":"Advantage-weighted regression: simple and scalable off-policy reinforcement learning","author":"Peng","year":"2019","journal-title":"arXiv:1910.00177"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3364844"},{"key":"ref24","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref25","first-page":"1719","article-title":"PLAS: Latent action space for offline reinforcement learning","volume-title":"Proc. Int. Conf. Robot Learn.","author":"Zhou"},{"key":"ref26","first-page":"11761","article-title":"Stabilizing offpolicy q-learning via bootstrapping error reduction","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kumar"},{"key":"ref27","article-title":"Behavior regularized offline reinforcement learning","author":"Wu","year":"2019","journal-title":"arXiv:1911.11361"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM54844.2022.00012"},{"key":"ref29","first-page":"5774","article-title":"Offline reinforcement learning with fisher divergence critic regularization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kostrikov"},{"key":"ref30","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Fujimoto"},{"key":"ref31","article-title":"Distancesensitive offline reinforcement learning","author":"Li","year":"2022","journal-title":"arXiv:2205.11027"},{"key":"ref32","article-title":"Offline reinforcement learning with adaptive behavior regularization","author":"Zhou","year":"2022","journal-title":"arXiv:2211.08251"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26130"},{"key":"ref34","first-page":"19967","article-title":"Pessimistic Q-learning for offline reinforcement learning: Towards optimal sample complexity","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shi"},{"key":"ref35","article-title":"Extreme Q-learning: MaxEnt RL without entropy","author":"Garg","year":"2023","journal-title":"arXiv:2301.02328"},{"key":"ref36","article-title":"Regularized behavior value estimation","author":"Gulcehre","year":"2021","journal-title":"arXiv:2103.09575"},{"key":"ref37","first-page":"7768","article-title":"Critic regularized regression","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref38","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kumar"},{"key":"ref39","first-page":"1711","article-title":"Mildly conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lyu"},{"key":"ref40","article-title":"Offline reinforcement learning with implicit Q-learning","author":"Kostrikov","year":"2021","journal-title":"arXiv:2110.06169"},{"key":"ref41","article-title":"The in-sample softmax for offline reinforcement learning","author":"Xiao","year":"2023","journal-title":"arXiv:2302.14372"},{"key":"ref42","first-page":"568","article-title":"Error propagation for approximate policy and value iteration","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Farahmand"},{"key":"ref43","first-page":"3744","article-title":"Behavioral cloning from observation","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Torabi"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2022.3152724"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/520"},{"key":"ref46","first-page":"1587","article-title":"Addressing function approximation error in actor\u2013critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref47","first-page":"1861","article-title":"Soft actor\u2013critic: Offpolicy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref48","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Silver"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553495"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221021\/10604660\/10516602.pdf?arnumber=10516602","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,21]],"date-time":"2024-07-21T04:17:44Z","timestamp":1721535464000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10516602\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":50,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2024.3388007","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"value":"2168-2216","type":"print"},{"value":"2168-2232","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}