{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,28]],"date-time":"2026-06-28T06:17:06Z","timestamp":1782627426408,"version":"3.54.5"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Basic Science Center Program of National Natural Science Foundation of China","award":["62388101"],"award-info":[{"award-number":["62388101"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62303308"],"award-info":[{"award-number":["62303308"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Pujiang Program","award":["23PJ1404700"],"award-info":[{"award-number":["23PJ1404700"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Ind. Inf."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tii.2025.3627122","type":"journal-article","created":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T18:44:43Z","timestamp":1762973083000},"page":"1440-1451","source":"Crossref","is-referenced-by-count":1,"title":["Horizon-Greedy\n                    <i>Q<\/i>\n                    -Ensembles Regularized Decision Transformer: An Offline Reinforcement Learning Approach for Robotic Tasks"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2026-6856","authenticated-orcid":false,"given":"Botao","family":"Dong","sequence":"first","affiliation":[{"name":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4042-628X","authenticated-orcid":false,"given":"Xin","family":"Dong","sequence":"additional","affiliation":[{"name":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingxuan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8600-9668","authenticated-orcid":false,"given":"Hongtian","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3481887"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2023.3280320"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00573-6"},{"key":"ref4","first-page":"1678","article-title":"What matters in learning from offline human demonstrations for robot manipulation","volume-title":"Proc. Conf. Robot Learn.","volume":"164","author":"Mandlekar","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2024.3468453"},{"key":"ref6","first-page":"6596","article-title":"Learning non-Markovian decision-making from state-only sequences","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Qin","year":"2023"},{"key":"ref7","first-page":"1","article-title":"When should we prefer decision transformers for offline reinforcement learning?","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Bhargava","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2023.3240585"},{"key":"ref9","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen","year":"2021"},{"key":"ref10","first-page":"1","article-title":"Diffusion policies as an expressive policy class for offline reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2024.3495775"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2025.3545048"},{"key":"ref13","first-page":"19165","article-title":"Q-value regularized transformer for offline reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hu","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29499"},{"key":"ref15","first-page":"38989","article-title":"Q-learning decision transformer: Leveraging dynamic programming for conditional sequence modelling in offline RL","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"202","author":"Yamagata","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1629"},{"key":"ref17","first-page":"1547","article-title":"DROID: Learning from offline heterogeneous demonstrations via reward-policy distillation","volume-title":"Proc. Conf. Robot Learn.","volume":"229","author":"Jayanthi","year":"2023"},{"key":"ref18","first-page":"6154","article-title":"Federated ensemble-directed offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Rengarajan","year":"2024"},{"key":"ref19","first-page":"29064","article-title":"A2PO: Towards effective offline reinforcement learning from an advantage-aware perspective","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Qing","year":"2024"},{"key":"ref20","first-page":"18548","article-title":"On the occupancy measure of non-Markovian policies in continuous MDPs","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"202","author":"Laroche","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2023.3343375"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123684"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2024.3372939"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3138"},{"key":"ref26","first-page":"18267","article-title":"Why so pessimistic? Estimating uncertainties for offline RL through ensembles, and why their independence matters","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Ghasemipour","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4353-9"},{"key":"ref28","first-page":"1","article-title":"Score regularized policy optimization through diffusion behavior","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Chen","year":"2024"},{"key":"ref29","article-title":"D4RL: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020"},{"key":"ref30","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":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/687"},{"key":"ref32","first-page":"1","article-title":"Offline reinforcement learning with implicit q-learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kostrikov","year":"2021"},{"key":"ref33","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"97","author":"Fujimoto","year":"2019"},{"key":"ref34","first-page":"11761","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":"ref35","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":"ref36","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":"ref37","first-page":"18806","article-title":"Inverse preference learning: Preference-based RL without a reward function","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Hejna","year":"2023"},{"key":"ref38","first-page":"1","article-title":"Preference transformer: Modeling human preferences using transformers for RL","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kim","year":"2023"},{"key":"ref39","first-page":"2775","article-title":"Bridging the gap between value and policy based reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Nachum","year":"2017"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1789"}],"container-title":["IEEE Transactions on Industrial Informatics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9424\/11372499\/11244187.pdf?arnumber=11244187","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:11:40Z","timestamp":1770671500000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11244187\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":40,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tii.2025.3627122","relation":{},"ISSN":["1551-3203","1941-0050"],"issn-type":[{"value":"1551-3203","type":"print"},{"value":"1941-0050","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}