{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T19:05:06Z","timestamp":1771614306659,"version":"3.50.1"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Project","award":["2018AAA0100802"],"award-info":[{"award-number":["2018AAA0100802"]}]},{"DOI":"10.13039\/501100003995","name":"Anhui Provincial Natural Science Foundation","doi-asserted-by":"publisher","award":["2008085MF198"],"award-info":[{"award-number":["2008085MF198"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tai.2024.3372939","type":"journal-article","created":{"date-parts":[[2024,3,5]],"date-time":"2024-03-05T14:25:59Z","timestamp":1709648759000},"page":"6066-6079","source":"Crossref","is-referenced-by-count":6,"title":["Model-Based Offline Reinforcement Learning With Uncertainty Estimation and Policy Constraint"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6038-4339","authenticated-orcid":false,"given":"Jin","family":"Zhu","sequence":"first","affiliation":[{"name":"Department of Automation, University of Science and Technology of China, Hefei, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4562-4941","authenticated-orcid":false,"given":"Chunhui","family":"Du","sequence":"additional","affiliation":[{"name":"Department of Automation, University of Science and Technology of China, Hefei, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0596-6050","authenticated-orcid":false,"given":"Geir E.","family":"Dullerud","sequence":"additional","affiliation":[{"name":"Department of Mechanical Science and Engineering, University of Illinois at Urbana-Champaign, Urbana, IL, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2018.8490422"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tai.2023.3249683"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2023.3237665"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3125918"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3078462"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3477600"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WZEE54157.2021.9576838"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_2"},{"key":"ref9","article-title":"Instrumental variable value iteration for causal offline reinforcement learning","author":"Liao","year":"2021"},{"key":"ref10","first-page":"22270","article-title":"Addressing optimism bias in sequence modeling for reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Villaflor","year":"2022"},{"key":"ref11","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Fujimoto","year":"2018"},{"key":"ref12","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Haarnoja","year":"2018"},{"key":"ref13","article-title":"D4RL: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020"},{"key":"ref14","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Fujimoto","year":"2019"},{"key":"ref15","first-page":"11149","article-title":"Stabilizing off-policy Q-learning via bootstrapping error reduction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Kumar","year":"2019"},{"key":"ref16","article-title":"Behavior regularized offline reinforcement learning","author":"Wu","year":"2019"},{"key":"ref17","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kumar","year":"2020"},{"key":"ref18","first-page":"14129","article-title":"MOPO: Model-based offline policy optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Yu","year":"2020"},{"key":"ref19","first-page":"21810","article-title":"MOReL: Model-based offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kidambi","year":"2020"},{"key":"ref20","first-page":"8432","article-title":"Offline model-based adaptable policy learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen","year":"2021"},{"key":"ref21","first-page":"4754","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Chua","year":"2018"},{"key":"ref22","first-page":"28954","article-title":"COMBO: Conservative offline model-based policy optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Yu","year":"2021"},{"key":"ref23","article-title":"Revisiting design choices in offline model-based reinforcement learning","author":"Lu","year":"2021"},{"key":"ref24","first-page":"617","article-title":"Model-based reinforcement learning via meta-policy optimization","volume-title":"Proc. Conf. Robot Learn. (PMLR)","author":"Clavera","year":"2018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10335-w"},{"key":"ref26","first-page":"15849","article-title":"Plan to predict: Learning an uncertainty-foreseeing model for model-based reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Wu","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20886"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045502"},{"key":"ref29","first-page":"7436","article-title":"Uncertainty-based offline reinforcement learning with diversified Q-ensemble","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"An","year":"2021"},{"key":"ref30","article-title":"Offline reinforcement learning with implicit Q-learning","author":"Kostrikov","year":"2021"},{"key":"ref31","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Fujimoto","year":"2021"},{"key":"ref32","article-title":"Uncertainty weighted actor-critic for offline reinforcement learning","author":"Wu","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.2307\/jj.20206644.79"},{"key":"ref34","first-page":"449","article-title":"Model-based offline reinforcement learning with pessimism-modulated dynamics belief","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Guo","year":"2022"},{"key":"ref35","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref36","first-page":"857","article-title":"Stochastic neighbor embedding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"15","author":"Hinton","year":"2002"},{"key":"ref37","first-page":"12519","article-title":"When to trust your model: Model-based policy optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Janner","year":"2019"},{"key":"ref38","article-title":"Model-ensemble trust-region policy optimization","author":"Kurutach","year":"2018"},{"key":"ref39","first-page":"2019","article-title":"Variational Bayesian dropout: pitfalls and fixes","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Hron","year":"2018"},{"key":"ref40","article-title":"Conservative bayesian model-based value expansion for offline policy optimization","author":"Jeong","year":"2022"},{"key":"ref41","first-page":"1154","article-title":"Offline reinforcement learning from images with latent space models","volume-title":"Proc. Learn. Dyn. Control (PMLR)","author":"Rafailov","year":"2021"},{"key":"ref42","article-title":"MOORe: Model-based offline-to-online reinforcement learning","author":"Mao","year":"2022"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"issue":"1","key":"ref44","first-page":"723","article-title":"A kernel two-sample test","volume":"13","author":"Gretton","year":"2012","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9078688\/10794552\/10459064.pdf?arnumber=10459064","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:09:39Z","timestamp":1755911379000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10459064\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":44,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tai.2024.3372939","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}