{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T06:04:09Z","timestamp":1773468249094,"version":"3.50.1"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003009","name":"Science and Technology Development Fund","doi-asserted-by":"publisher","award":["0080\/2024\/RIA2"],"award-info":[{"award-number":["0080\/2024\/RIA2"]}],"id":[{"id":"10.13039\/501100003009","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Big Data"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tbdata.2025.3630807","type":"journal-article","created":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T18:50:08Z","timestamp":1762800608000},"page":"536-553","source":"Crossref","is-referenced-by-count":0,"title":["LLM-Based Data Augmentation Method in Reinforcement Learning With Machine-Unlearning and Fine-Tuning"],"prefix":"10.1109","volume":"12","author":[{"given":"Yunjiao","family":"Lei","sequence":"first","affiliation":[{"name":"Pengcheng Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7561-0992","authenticated-orcid":false,"given":"Dayong","family":"Ye","sequence":"additional","affiliation":[{"name":"Faculty of Data Science, City University of Macau, Macao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3411-7947","authenticated-orcid":false,"given":"Tianqing","family":"Zhu","sequence":"additional","affiliation":[{"name":"Faculty of Data Science, City University of Macau, Macao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1680-2521","authenticated-orcid":false,"given":"Wanlei","family":"Zhou","sequence":"additional","affiliation":[{"name":"Faculty of Data Science, City University of Macau, Macao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3491-5968","authenticated-orcid":false,"given":"Philip S.","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Illinois, Chicago, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yarats"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981090"},{"key":"ref3","first-page":"19884","article-title":"Reinforcement learning with augmented data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Laskin"},{"key":"ref4","first-page":"5694","article-title":"Imagination-augmented agents for deep reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Racani\u00e8re"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102662"},{"key":"ref6","first-page":"59832","article-title":"Learning better with less: Effective augmentation for sample-efficient visual reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ma"},{"key":"ref7","first-page":"7740","article-title":"Retrieval-augmented reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Goyal"},{"key":"ref8","article-title":"Augmenting reinforcement learning with human feedback","volume-title":"Proc. 2011 Workshop New Developments Imitation Learn.","author":"Knox"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3013937"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812140"},{"key":"ref11","first-page":"5402","article-title":"Automatic data augmentation for generalization in reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Raileanu"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561103"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02142"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482386"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2025.230080"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00019"},{"key":"ref17","article-title":"Certified data removal from machine learning models","author":"Guo","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3266233"},{"key":"ref19","first-page":"10355","article-title":"DeltaGrad: Rapid retraining of machine learning models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3292075"},{"key":"ref22","article-title":"Sample-efficient reinforcement learning via counterfactual-based data augmentation","author":"Lu","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2015.35"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2020.3017497"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2020.3017497"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1561\/9781601988195"},{"key":"ref27","first-page":"2944","article-title":"Learning continuous control policies by stochastic value gradients","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Heess"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110440"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3105426"}],"container-title":["IEEE Transactions on Big Data"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6687317\/11433832\/11235955.pdf?arnumber=11235955","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T05:15:18Z","timestamp":1773465318000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11235955\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":29,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tbdata.2025.3630807","relation":{},"ISSN":["2332-7790","2372-2096"],"issn-type":[{"value":"2332-7790","type":"electronic"},{"value":"2372-2096","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}