{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:05:46Z","timestamp":1777651546216,"version":"3.51.4"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["61976215"],"award-info":[{"award-number":["61976215"]}],"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. Artif. Intell."],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1109\/tai.2022.3225251","type":"journal-article","created":{"date-parts":[[2022,11,28]],"date-time":"2022-11-28T14:53:55Z","timestamp":1669647235000},"page":"61-69","source":"Crossref","is-referenced-by-count":2,"title":["Offline\u2013Online Actor\u2013Critic"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5327-1088","authenticated-orcid":false,"given":"Xuesong","family":"Wang","sequence":"first","affiliation":[{"name":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education and School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9427-1532","authenticated-orcid":false,"given":"Diyuan","family":"Hou","sequence":"additional","affiliation":[{"name":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education and School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5123-5043","authenticated-orcid":false,"given":"Longyang","family":"Huang","sequence":"additional","affiliation":[{"name":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education and School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"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 School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3087666"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3097313"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3015748"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3046646"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3111142"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref11","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref12","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman","year":"2015"},{"key":"ref13","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020"},{"key":"ref14","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2019"},{"key":"ref15","first-page":"1554","article-title":"Safe driving via expert guided policy optimization","volume-title":"Proc. Conf. Robot Learn.","author":"Peng","year":"2021"},{"key":"ref16","first-page":"10784","article-title":"Learning to simulate self-driven particles system with coordinated policy optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Peng","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219961"},{"key":"ref18","article-title":"Behavior regularized offline reinforcement learning","author":"Wu","year":"2019"},{"key":"ref19","first-page":"11784","article-title":"Stabilizing off-policy Q-learning via bootstrapping error reduction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar","year":"2019"},{"key":"ref20","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar","year":"2020"},{"key":"ref21","first-page":"14129","article-title":"MOPO: Model-based offline policy optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu","year":"2020"},{"key":"ref22","first-page":"21810","article-title":"Morel: Model-based offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kidambi","year":"2020"},{"key":"ref23","article-title":"Deployment-efficient reinforcement learning via model-based offline optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Matsushima","year":"2021"},{"key":"ref24","article-title":"AWAC: Accelerating online reinforcement learning with offline datasets","author":"Nair","year":"2020"},{"key":"ref25","first-page":"1702","article-title":"Offline-to-online reinforcement learning via balanced replay and pessimistic Q-ensemble","volume-title":"Proc. Conf. Robot Learn.","author":"Lee","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref27","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fujimoto","year":"2021"},{"key":"ref28","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":"ref29","article-title":"D4RL: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9078688\/10384607\/09964421.pdf?arnumber=9964421","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:08:51Z","timestamp":1755911331000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9964421\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":29,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tai.2022.3225251","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1]]}}}