{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T15:44:05Z","timestamp":1778255045546,"version":"3.51.4"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004787","name":"Hong Kong Research Grant Council under General Research Fund","doi-asserted-by":"publisher","award":["11218621"],"award-info":[{"award-number":["11218621"]}],"id":[{"id":"10.13039\/501100004787","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004787","name":"Research Impact Fund (RIF) Project","doi-asserted-by":"publisher","award":["R5060-19"],"award-info":[{"award-number":["R5060-19"]}],"id":[{"id":"10.13039\/501100004787","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tsmc.2025.3537990","type":"journal-article","created":{"date-parts":[[2025,2,17]],"date-time":"2025-02-17T18:37:02Z","timestamp":1739817422000},"page":"2998-3012","source":"Crossref","is-referenced-by-count":1,"title":["A Unified Sparse Training Framework for Lightweight Lifelong Deep Reinforcement Learning"],"prefix":"10.1109","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4857-5439","authenticated-orcid":false,"given":"Meng","family":"Xu","sequence":"first","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8563-148X","authenticated-orcid":false,"given":"Xinhong","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiwei","family":"Fu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2109-3829","authenticated-orcid":false,"given":"Yi-Rong","family":"Lin","sequence":"additional","affiliation":[{"name":"AI Research Center, Hon Hai Research Institute, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0475-3689","authenticated-orcid":false,"given":"Yung-Hui","family":"Li","sequence":"additional","affiliation":[{"name":"AI Research Center, Hon Hai Research Institute, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9318-1482","authenticated-orcid":false,"given":"Jianping","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00132"},{"key":"ref2","article-title":"Remember and forget experience replay for multi-agent reinforcement learning","author":"Weber","year":"2022","journal-title":"arXiv:2203.13319"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3170485"},{"key":"ref4","article-title":"RLx2: Training a sparse deep reinforcement learning model from scratch","author":"Tan","year":"2023","journal-title":"arXiv:2205.15043"},{"key":"ref5","article-title":"Continual learning with hypernetworks","author":"Von Oswald","year":"2022","journal-title":"arXiv:1906.00695"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-443-15754-7.00073-0"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.13673"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412614"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-17866-2"},{"key":"ref11","first-page":"28955","article-title":"Reincarnating reinforcement learning: Reusing prior computation to accelerate progress","volume-title":"Proc. 36th Adv. Neural Inf. Process. Syst.","author":"Agarwal"},{"key":"ref12","first-page":"6334","article-title":"Provable lifelong learning of representations","volume-title":"Proc. 25th Int. Conf. Artif. Intell. Statist.","author":"Cao"},{"key":"ref13","article-title":"Offline-online class-incremental continual learning via dual-prototype self-augment and refinement","author":"Huo","year":"2023","journal-title":"arXiv:2303.10891"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.02.027"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3299556"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3056373"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/e26010093"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2967566"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852451"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/477"},{"key":"ref21","article-title":"Automatic noise filtering with dynamic sparse training in deep reinforcement learning","author":"Grooten","year":"2023","journal-title":"arXiv:2302.06548"},{"key":"ref22","first-page":"94","article-title":"Continual learning with dynamic sparse training: Exploring algorithms for effective model updates","volume-title":"Proc. Conf. Parsimony Learn.","author":"Yildirim"},{"key":"ref23","article-title":"EsaCL: Efficient continual learning of sparse models","author":"Ren","year":"2024","journal-title":"arXiv:2401.05667"},{"key":"ref24","first-page":"20366","article-title":"SparCL: Sparse continual learning on the edge","volume-title":"Proc. 36th Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref25","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","author":"Keskar","year":"2017","journal-title":"arXiv:1609.04836"},{"key":"ref26","first-page":"639","article-title":"Towards understanding sharpness-aware minimization","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Andriushchenko"},{"key":"ref27","article-title":"Replay-enhanced continual reinforcement learning","author":"Zhang","year":"2023","journal-title":"arXiv:2311.11557"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3385570"},{"key":"ref29","first-page":"89","article-title":"Task-agnostic continual reinforcement learning: Gaining insights and overcoming challenges","volume-title":"Proc. 2nd Conf. Lifelong Learn. Agents","author":"Caccia"},{"issue":"1","key":"ref30","first-page":"17","article-title":"On the evolution of random graphs","volume":"5","author":"Erd\u00f4s","year":"1960","journal-title":"Publ. Math. Inst. Hung. Acad. Sci"},{"key":"ref31","first-page":"17662","article-title":"Online meta-critic learning for off-policy actor-critic methods","volume-title":"Proc. 34th Adv. Neural Inf. Process. Syst.","author":"Zhou"},{"key":"ref32","first-page":"5774","article-title":"Offline reinforcement learning with fisher divergence critic regularization","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Kostrikov"},{"key":"ref33","article-title":"Prioritized experience replay","author":"Schaul","year":"2016","journal-title":"arXiv:1511.05952"},{"key":"ref34","first-page":"2159","article-title":"Deterministic policy gradient: Convergence analysis","volume-title":"Proc. 38th Uncertain. Artif. Intell.","author":"Xiong"},{"key":"ref35","first-page":"28701","article-title":"Policy regularization with dataset constraint for offline reinforcement learning","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Ran"},{"key":"ref36","article-title":"Understanding domain randomization for sim-to-real transfer","author":"Chen","year":"2022","journal-title":"arXiv:2110.03239"},{"key":"ref37","first-page":"1","article-title":"Building a subspace of policies for scalable continual learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Gaya"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/AIoTSys58602.2023.00030"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.01.078"},{"key":"ref40","article-title":"Why gradient clipping accelerates training: A theoretical justification for adaptivity","author":"Zhang","year":"2020","journal-title":"arXiv:1905.11881"},{"key":"ref41","first-page":"15511","article-title":"Improved analysis of clipping algorithms for non-convex optimization","volume-title":"Proc. 34th Adv. Neural Inf. Process. Syst.","author":"Zhang"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221021\/10933808\/10891264.pdf?arnumber=10891264","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T18:39:21Z","timestamp":1742841561000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10891264\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":41,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2025.3537990","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"value":"2168-2216","type":"print"},{"value":"2168-2232","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}