{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T02:14:51Z","timestamp":1768443291417,"version":"3.49.0"},"reference-count":83,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFF0905400"],"award-info":[{"award-number":["2023YFF0905400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021ZD0112500"],"award-info":[{"award-number":["2021ZD0112500"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476110"],"award-info":[{"award-number":["62476110"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U2341229"],"award-info":[{"award-number":["U2341229"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Project of Jilin Province","award":["20240304200SF"],"award-info":[{"award-number":["20240304200SF"]}]},{"DOI":"10.13039\/501100017684","name":"International Cooperation Project of Jilin Province","doi-asserted-by":"publisher","award":["20220402009GH"],"award-info":[{"award-number":["20220402009GH"]}],"id":[{"id":"10.13039\/501100017684","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tnnls.2025.3598928","type":"journal-article","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T17:34:44Z","timestamp":1758044084000},"page":"20429-20443","source":"Crossref","is-referenced-by-count":1,"title":["Continual Diffuser (CoD): Mastering Continual Offline RL With Experience Rehearsal"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8658-9447","authenticated-orcid":false,"given":"Jifeng","family":"Hu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, MOE, Jilin University, Changchun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5659-3464","authenticated-orcid":false,"given":"Li","family":"Shen","sequence":"additional","affiliation":[{"name":"Shenzhen Campus, Sun Yat-sen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5387-7904","authenticated-orcid":false,"given":"Sili","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Information Engineering and Hainan International College, Minzu University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6980-8062","authenticated-orcid":false,"given":"Zhejian","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, MOE, Jilin University, Changchun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7835-9556","authenticated-orcid":false,"given":"Hechang","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, MOE, Jilin University, Changchun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1539-7939","authenticated-orcid":false,"given":"Lichao","family":"Sun","sequence":"additional","affiliation":[{"name":"Lehigh University, Bethlehem, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2697-8093","authenticated-orcid":false,"given":"Yi","family":"Chang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, MOE, Jilin University, Changchun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Jurong West, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06419-4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00520-5"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07711-7"},{"key":"ref5","article-title":"A study on the plasticity of neural networks","author":"Berariu","year":"2021","journal-title":"arXiv:2106.00042"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0080-x"},{"key":"ref7","article-title":"Diffusion model is an effective planner and data synthesizer for multi-task reinforcement learning","author":"He","year":"2023","journal-title":"arXiv:2305.18459"},{"key":"ref8","article-title":"Diffusion policies as an expressive policy class for offline reinforcement learning","author":"Wang","year":"2022","journal-title":"arXiv:2208.06193"},{"key":"ref9","article-title":"Efficient diffusion policies for offline reinforcement learning","author":"Kang","year":"2023","journal-title":"arXiv:2305.20081"},{"key":"ref10","article-title":"Is conditional generative modeling all you need for decision-making?","author":"Ajay","year":"2022","journal-title":"arXiv:2211.15657"},{"key":"ref11","article-title":"Continual task allocation in meta-policy network via sparse prompting","author":"Yang","year":"2023","journal-title":"arXiv:2305.18444"},{"key":"ref12","article-title":"Prediction and control in continual reinforcement learning","author":"Anand","year":"2023","journal-title":"arXiv:2312.11669"},{"key":"ref13","article-title":"T-DGR: A trajectory-based deep generative replay method for continual learning in decision making","author":"Yue","year":"2024","journal-title":"arXiv:2401.02576"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3170485"},{"key":"ref15","article-title":"MoSA: Mixture of sparse adapters for visual efficient tuning","author":"Zhang","year":"2023","journal-title":"arXiv:2312.02923"},{"key":"ref16","article-title":"Continual diffusion: Continual customization of text-to-image diffusion with C-LoRA","author":"Smith","year":"2023","journal-title":"arXiv:2304.06027"},{"key":"ref17","article-title":"How to reuse and compose knowledge for a lifetime of tasks: A survey on continual learning and functional composition","author":"Mendez","year":"2022","journal-title":"arXiv:2207.07730"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00810"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3280085"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3162241"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref22","article-title":"Unclear: A straightforward method for continual reinforcement learning","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"108","author":"Kessler"},{"key":"ref23","article-title":"Variational continual learning","author":"Nguyen","year":"2017","journal-title":"arXiv:1710.10628"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw59228.2023.00239"},{"key":"ref25","first-page":"27585","article-title":"The ideal continual learner: An agent that never forgets","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Peng"},{"key":"ref26","article-title":"Solving continual offline reinforcement learning with decision transformer","author":"Huang","year":"2024","journal-title":"arXiv:2401.08478"},{"key":"ref27","first-page":"350","article-title":"Experience replay for continual learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rolnick"},{"key":"ref28","article-title":"Efficient lifelong learning with A-GEM","author":"Chaudhry","year":"2018","journal-title":"arXiv:1812.00420"},{"key":"ref29","article-title":"Planning with diffusion for flexible behavior synthesis","author":"Janner","year":"2022","journal-title":"arXiv:2205.09991"},{"key":"ref30","article-title":"Replay-enhanced continual reinforcement learning","author":"Zhang","year":"2023","journal-title":"arXiv:2311.11557"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3317874"},{"key":"ref32","first-page":"4528","article-title":"Progress & compress: A scalable framework for continual learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schwarz"},{"key":"ref33","article-title":"A definition of continual reinforcement learning","author":"Abel","year":"2023","journal-title":"arXiv:2307.11046"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3398208"},{"key":"ref35","article-title":"SMART: Self-supervised multi-task pretraining with control transformers","author":"Sun","year":"2023","journal-title":"arXiv:2301.09816"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01486"},{"key":"ref37","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref38","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NIPS","author":"Ho"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00037"},{"key":"ref40","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"arXiv:2205.11487"},{"key":"ref41","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Nichol"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-023-06458-y"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3758\/s13423-018-1554-2"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref46","article-title":"Harnessing discrete representations for continual reinforcement learning","author":"Meyer","year":"2023","journal-title":"arXiv:2312.01203"},{"key":"ref47","first-page":"19884","article-title":"Reinforcement learning with augmented data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Laskin"},{"key":"ref48","article-title":"Policy consolidation for continual reinforcement learning","author":"Kaplanis","year":"2019","journal-title":"arXiv:1902.00255"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00404"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.11.050"},{"key":"ref51","first-page":"62270","article-title":"PLASTIC: Improving input and label plasticity for sample efficient reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29499"},{"key":"ref53","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020","journal-title":"arXiv:2005.01643"},{"key":"ref54","article-title":"Offline reinforcement learning with implicit Q-learning","author":"Kostrikov","year":"2021","journal-title":"arXiv:2110.06169"},{"key":"ref55","article-title":"Offline RL with observation histories: Analyzing and improving sample complexity","author":"Hong","year":"2023","journal-title":"arXiv:2310.20663"},{"key":"ref56","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":"ref57","article-title":"Behavior regularized offline reinforcement learning","author":"Wu","year":"2019","journal-title":"arXiv:1911.11361"},{"key":"ref58","article-title":"RAMBO-RL: Robust adversarial model-based offline reinforcement learning","author":"Rigter","year":"2022","journal-title":"arXiv:2204.12581"},{"key":"ref59","first-page":"21810","article-title":"MOReL: Model-based offline reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kidambi"},{"key":"ref60","first-page":"1154","article-title":"Offline reinforcement learning from images with latent space models","volume-title":"Proc. Learn. Dyn. Control","author":"Rafailov"},{"key":"ref61","first-page":"1273","article-title":"Offline reinforcement learning as one big sequence modeling problem","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Janner"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3302804"},{"key":"ref63","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":"ref64","first-page":"28496","article-title":"Continual world: A robotic benchmark for continual reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"34","author":"Wo\u0142czyk"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref66","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.","author":"Haarnoja"},{"key":"ref67","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Yu"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00568-3"},{"key":"ref69","first-page":"24631","article-title":"Prompting decision transformer for few-shot policy generalization","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Xu"},{"key":"ref70","first-page":"6197","article-title":"Multi-task batch reinforcement learning with metric learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref71","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Rakelly"},{"key":"ref72","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv:2106.09685"},{"key":"ref73","volume-title":"Peft: State-of-the-Art Parameter-Efficient Fine-Tuning Methods","author":"Mangrulkar","year":"2022"},{"key":"ref74","article-title":"LoftQ: LoRA-fine-tuning-aware quantization for large language models","author":"Li","year":"2023","journal-title":"arXiv:2310.08659"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_9"},{"key":"ref76","first-page":"2994","article-title":"Continual learning with deep generative replay","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Shin"},{"key":"ref77","article-title":"Data-incremental continual offline reinforcement learning","author":"Gai","year":"2024","journal-title":"arXiv:2404.12639"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636069"},{"key":"ref79","first-page":"4572","article-title":"Generative adversarial imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref80","first-page":"38456","article-title":"Learning multimodal behaviors from scratch with diffusion policy gradient","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Li"},{"key":"ref81","article-title":"Deep generative models for offline policy learning: Tutorial, survey, and perspectives on future directions","author":"Chen","year":"2024","journal-title":"arXiv:2402.13777"},{"key":"ref82","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv:2010.02502"},{"key":"ref83","article-title":"Sharpness-aware minimization for efficiently improving generalization","author":"Foret","year":"2020","journal-title":"arXiv:2010.01412"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11272992\/11165204.pdf?arnumber=11165204","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:43:29Z","timestamp":1764787409000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11165204\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":83,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3598928","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}