{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T15:15:26Z","timestamp":1780586126977,"version":"3.54.1"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"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":["42327901"],"award-info":[{"award-number":["42327901"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"BNRist","award":["BNR2024TD03003"],"award-info":[{"award-number":["BNR2024TD03003"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tnnls.2024.3488358","type":"journal-article","created":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T14:14:03Z","timestamp":1732198443000},"page":"13094-13108","source":"Crossref","is-referenced-by-count":6,"title":["Decoupled Prioritized Resampling for Offline RL"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0437-7238","authenticated-orcid":false,"given":"Yang","family":"Yue","sequence":"first","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bingyi","family":"Kang","sequence":"additional","affiliation":[{"name":"Sea AI Laboratory, Fusionopolis Place, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5466-867X","authenticated-orcid":false,"given":"Xiao","family":"Ma","sequence":"additional","affiliation":[{"name":"Sea AI Laboratory, Fusionopolis Place, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2587-2660","authenticated-orcid":false,"given":"Qisen","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7251-0988","authenticated-orcid":false,"given":"Gao","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0858-1770","authenticated-orcid":false,"given":"Shiji","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8906-3777","authenticated-orcid":false,"given":"Shuicheng","family":"Yan","sequence":"additional","affiliation":[{"name":"Sea AI Laboratory, Fusionopolis Place, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Harnessing mixed offline reinforcement learning datasets via trajectory weighting","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Hong"},{"key":"ref2","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_2"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3250269"},{"key":"ref5","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Fujimoto"},{"key":"ref6","article-title":"Way off-policy batch deep reinforcement learning of implicit human preferences in dialog","author":"Jaques","year":"2019","journal-title":"arXiv:1907.00456"},{"key":"ref7","article-title":"Advantage-weighted regression: Simple and scalable off-policy reinforcement learning","author":"Bin Peng","year":"2019","journal-title":"arXiv:1910.00177"},{"key":"ref8","article-title":"Behavior regularized offline reinforcement learning","author":"Wu","year":"2019","journal-title":"arXiv:1911.11361"},{"key":"ref9","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"},{"key":"ref10","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Fujimoto"},{"key":"ref11","first-page":"1","article-title":"Prioritized experience replay","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Schaul"},{"key":"ref12","first-page":"18560","article-title":"DisCor: Corrective feedback in reinforcement learning via distribution correction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kumar"},{"key":"ref13","first-page":"110","article-title":"Experience replay with likelihood-free importance weights","volume-title":"Proc. Learn. Dyn. Control Conf.","author":"Sinha"},{"key":"ref14","article-title":"Prioritized sequence experience replay","author":"Brittain","year":"2019","journal-title":"arXiv:1905.12726"},{"key":"ref15","first-page":"10070","article-title":"Striving for simplicity and performance in off-policy DRL: Output normalization and non-uniform sampling","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref16","first-page":"17604","article-title":"Regret minimization experience replay in off-policy reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref17","first-page":"3878","article-title":"Self-imitation learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Oh"},{"key":"ref18","first-page":"1","article-title":"ReDS: Offline RL with heteroskedastic datasets via support constraints","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Singh"},{"key":"ref19","first-page":"18353","article-title":"BAIL: Best-action imitation learning for batch deep reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Chen"},{"key":"ref20","first-page":"6291","article-title":"Exponentially weighted imitation learning for batched historical data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Wang"},{"key":"ref21","first-page":"6266","article-title":"Curriculum offline imitating learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Liu"},{"key":"ref22","first-page":"2021","article-title":"Diagnosing bottlenecks in deep Q-learning algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fu"},{"key":"ref23","article-title":"Deep reinforcement learning and the deadly triad","author":"van Hasselt","year":"2018","journal-title":"arXiv:1812.02648"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"ref25","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kumar"},{"key":"ref26","article-title":"Offline reinforcement learning with implicit Q-learning","author":"Kostrikov","year":"2021","journal-title":"arXiv:2110.06169"},{"key":"ref27","first-page":"4933","article-title":"Offline RL without off-policy evaluation","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Brandfonbrener"},{"key":"ref28","article-title":"OpenAI gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref29","article-title":"D4RL: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020","journal-title":"arXiv:2004.07219"},{"key":"ref30","first-page":"1","article-title":"Boosting offline reinforcement learning via data rebalancing","volume-title":"Proc. 3rd NeurIPS Offline RL Workshop","author":"Yue"},{"key":"ref31","first-page":"267","article-title":"Approximately optimal approximate reinforcement learning","volume-title":"Proc. 19th Int. Conf. Mach. Learn.","author":"Kakade"},{"key":"ref32","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref33","first-page":"1","article-title":"Diffusion policies as an expressive policy class for offline reinforcement learning","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref34","first-page":"1","article-title":"Understanding, predicting and better resolving Q-value divergence in offline-RL","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Yue"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1108\/RIA-10-2022-0248"},{"key":"ref36","first-page":"7768","article-title":"Critic regularized regression","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Wang"},{"key":"ref37","article-title":"AWAC: Accelerating online reinforcement learning with offline datasets","author":"Nair","year":"2020","journal-title":"arXiv:2006.09359"},{"key":"ref38","first-page":"1","article-title":"Offline reinforcement learning via high-fidelity generative behavior modeling","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Chen"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3293508"},{"key":"ref40","first-page":"1","article-title":"The importance of pessimism in fixed-dataset policy optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Buckman"},{"key":"ref41","first-page":"28954","article-title":"COMBO: Conservative offline model-based policy optimization","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Yu"},{"key":"ref42","first-page":"7436","article-title":"Uncertainty-based offline reinforcement learning with diversified q-ensemble","volume":"34","author":"An","year":"2021","journal-title":"Adv. neural Inf. Process. Syst."},{"key":"ref43","article-title":"Q-ensemble for offline RL: Don\u2019t scale the ensemble, scale the batch size","author":"Nikulin","year":"2022","journal-title":"arXiv:2211.11092"},{"key":"ref44","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"},{"key":"ref45","first-page":"19235","article-title":"Conservative offline distributional reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Ma"},{"key":"ref46","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"},{"key":"ref47","first-page":"17811","article-title":"Offline meta-reinforcement learning with online self-supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pong"},{"key":"ref48","first-page":"2613","article-title":"Double Q-learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"23","author":"Hasselt"},{"key":"ref49","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11073756\/10759860.pdf?arnumber=10759860","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,9]],"date-time":"2025-07-09T23:20:55Z","timestamp":1752103255000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10759860\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":49,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3488358","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}