{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T08:06:51Z","timestamp":1790323611488,"version":"4.1.0"},"reference-count":54,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72301289"],"award-info":[{"award-number":["72301289"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.eswa.2026.133316","type":"journal-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T23:35:43Z","timestamp":1781566543000},"page":"133316","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["Proud: Sample-efficient offline-to-online reinforcement learning via prioritized diffusion model"],"prefix":"10.1016","volume":"331","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2741-6204","authenticated-orcid":false,"given":"Wei","family":"Shi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5600-4946","authenticated-orcid":false,"given":"Honglan","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3594-2167","authenticated-orcid":false,"given":"Xingxing","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Longfei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.133316_bib0001","first-page":"29304","article-title":"Deep reinforcement learning at the edge of the statistical precipice","volume":"34","author":"Agarwal","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.133316_bib0002","series-title":"Proceedings of the 40th international conference on machine learning","first-page":"1577","article-title":"Efficient online reinforcement learning with offline data","volume":"vol. 202","author":"Ball","year":"2023"},{"key":"10.1016\/j.eswa.2026.133316_bib0003","series-title":"Conference on robot learning","first-page":"2012","article-title":"PlayFusion: Skill acquisition via diffusion from language-annotated play","author":"Chen","year":"2023"},{"issue":"10-11","key":"10.1016\/j.eswa.2026.133316_bib0004","doi-asserted-by":"crossref","first-page":"1684","DOI":"10.1177\/02783649241273668","article-title":"Diffusion policy: Visuomotor policy learning via action diffusion","volume":"44","author":"Chi","year":"2025","journal-title":"The International Journal of Robotics Research"},{"key":"10.1016\/j.eswa.2026.133316_bib0005","series-title":"Statistical power analysis for the behavioral sciences","author":"Cohen","year":"2013"},{"key":"10.1016\/j.eswa.2026.133316_bib0006","unstructured":"Fu, J., Kumar, A., Nachum, O., Tucker, G., & Levine, S. (2020). D4RL: Datasets for deep data-driven reinforcement learning. arXiv: 2004.07219."},{"key":"10.1016\/j.eswa.2026.133316_bib0007","unstructured":"Fujimoto, S., & Gu, S. S. (2021). A minimalist approach to offline reinforcement learning. CoRR, (pp. 20132\u201320145). (vol. 34). arXiv:2106.06860."},{"key":"10.1016\/j.eswa.2026.133316_bib0008","series-title":"International conference on machine learning","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"Fujimoto","year":"2018"},{"key":"10.1016\/j.eswa.2026.133316_bib0009","unstructured":"Garreau, D., Jitkrittum, W., & Kanagawa, M. (2017). Large sample analysis of the median heuristic. arXiv: 1707.07269."},{"key":"10.1016\/j.eswa.2026.133316_bib0010","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2014). Generative adversarial networks. (vol. 27). arXiv:1406.2661."},{"issue":"25","key":"10.1016\/j.eswa.2026.133316_bib0011","first-page":"723","article-title":"A kernel two-sample test","volume":"13","author":"Gretton","year":"2012","journal-title":"Journal of Machine Learning Research"},{"issue":"3","key":"10.1016\/j.eswa.2026.133316_bib0012","doi-asserted-by":"crossref","first-page":"1299","DOI":"10.1109\/TKDE.2023.3302804","article-title":"Sample efficient offline-to-online reinforcement learning","volume":"36","author":"Guo","year":"2023","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10.1016\/j.eswa.2026.133316_bib0013","series-title":"International conference on machine learning","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018"},{"key":"10.1016\/j.eswa.2026.133316_bib0014","doi-asserted-by":"crossref","unstructured":"He, H., Bai, C., Xu, K., Yang, Z., Zhang, W., Wang, D., Zhao, B., & Li, X. (2023). Diffusion model is an effective planner and data synthesizer for multi-task reinforcement learning. In: Oh, A., Naumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S., (Eds.), In Advances in neural information processing systems, (pp. 64896\u201364917). (vol. 36).","DOI":"10.52202\/075280-2832"},{"key":"10.1016\/j.eswa.2026.133316_bib0015","unstructured":"Ho, J., & Salimans, T. (2022). Classifier-free diffusion guidance. arXiv: 2207.12598."},{"key":"10.1016\/j.eswa.2026.133316_bib0016","unstructured":"Hu, H., Yang, Y., Ye, J., Wu, C., Mai, Z., Hu, Y., Lv, T., Fan, C., Zhao, Q., & Zhang, C. (2024). Bayesian design principles for offline-to-online reinforcement learning. arXiv: 2405.20984."},{"issue":"6","key":"10.1016\/j.eswa.2026.133316_bib0017","doi-asserted-by":"crossref","DOI":"10.1016\/j.xinn.2025.100948","article-title":"Foundation models and intelligent decision-making: Progress, challenges, and perspectives","volume":"6","author":"Huang","year":"2025","journal-title":"The Innovation"},{"key":"10.1016\/j.eswa.2026.133316_bib0018","unstructured":"Janner, M., Du, Y., Tenenbaum, J. B., & Levine, S. (2022). Planning with diffusion for flexible behavior synthesis. arXiv: 2205.09991."},{"key":"10.1016\/j.eswa.2026.133316_bib0019","unstructured":"Kingma, D. P. (2013). Auto-encoding variational bayes. arXiv: 1312.6114."},{"key":"10.1016\/j.eswa.2026.133316_bib0020","unstructured":"Kostrikov, I., Nair, A., & Levine, S. (2021). Offline reinforcement learning with implicit q-learning. arXiv: 2110.06169."},{"key":"10.1016\/j.eswa.2026.133316_bib0021","series-title":"Conference on robot learning","first-page":"1702","article-title":"Offline-to-online reinforcement learning via balanced replay and pessimistic Q-ensemble","author":"Lee","year":"2022"},{"key":"10.1016\/j.eswa.2026.133316_bib0022","unstructured":"Li, J., Hu, X., Xu, H., Liu, J., Zhan, X., & Zhang, Y.-Q. (2023). PROTO: Iterative policy regularized offline-to-online reinforcement learning. arXiv: 2305.15669."},{"key":"10.1016\/j.eswa.2026.133316_bib0023","unstructured":"Liang, Z., Mu, Y., Ding, M., Ni, F., Tomizuka, M., & Luo, P. (2023). AdaptDiffuser: Diffusion models as adaptive self-evolving planners. arXiv: 2302.01877."},{"key":"10.1016\/j.eswa.2026.133316_sbref0024","series-title":"Synthetic experience replay","volume":"vol. 36","author":"Lu","year":"2023"},{"key":"10.1016\/j.eswa.2026.133316_bib0025","unstructured":"Lu, Y., Hausman, K., Chebotar, Y., Yan, M., Jang, E., Herzog, A., Xiao, T., Irpan, A., Khansari, M., Kalashnikov, D. et al. (2021). AW-OPT: Learning robotic skills with imitation and reinforcement at scale. arXiv: 2111.05424."},{"key":"10.1016\/j.eswa.2026.133316_bib0026","doi-asserted-by":"crossref","first-page":"93568","DOI":"10.52202\/079017-2967","article-title":"Offline reinforcement learning with ood state correction and ood action suppression","volume":"37","author":"Mao","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.133316_bib0027","doi-asserted-by":"crossref","first-page":"51436","DOI":"10.52202\/079017-1628","article-title":"Doubly mild generalization for offline reinforcement learning","volume":"37","author":"Mao","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.133316_bib0028","series-title":"Deep reinforcement learning workshop neurIPS 2022","article-title":"Fine-tuning offline policies with optimistic action selection","author":"Mark","year":"2022"},{"key":"10.1016\/j.eswa.2026.133316_bib0029","unstructured":"Nair, A., Gupta, A., Dalal, M., & Levine, S. (2020). AWAC: Accelerating online reinforcement learning with offline datasets. arXiv: 2006.09359."},{"issue":"1","key":"10.1016\/j.eswa.2026.133316_bib0030","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1109\/LRA.2023.3330663","article-title":"Diffusion co-policy for synergistic human-robot collaborative tasks","volume":"9","author":"Ng","year":"2023","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10.1016\/j.eswa.2026.133316_bib0031","doi-asserted-by":"crossref","unstructured":"Niu, H., Qiu, Y., Li, M., Zhou, G., Hu, J., Zhan, X. et al. (2025). When to trust your simulator: Dynamics-aware hybrid offline-and-online reinforcement learning. (pp. 36599\u201336612). (vol. 35). arXiv:2206.13464.","DOI":"10.52202\/068431-2652"},{"key":"10.1016\/j.eswa.2026.133316_bib0032","unstructured":"Peebles, W., Radosavovic, I., Brooks, T., Efros, A. A., & Malik, J. (2022). Learning to learn with generative models of neural network checkpoints. arXiv: 2209.12892."},{"key":"10.1016\/j.eswa.2026.133316_bib0033","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"20095","article-title":"Latent reward: LLM-empowered credit assignment in episodic reinforcement learning","volume":"vol. 39","author":"Qu","year":"2025"},{"key":"10.1016\/j.eswa.2026.133316_bib0034","unstructured":"Qu, Y., Wang, Q., Mao, Y., Hu, V. T., Ommer, B., & Ji, X. (2025b). Can prompt difficulty be online predicted for accelerating RL finetuning of reasoning models?arXiv: 2507.04632."},{"key":"10.1016\/j.eswa.2026.133316_bib0035","unstructured":"Qu, Y., Wang, Q. C., Mao, Y., Lv, Y., & Ji, X. (2025c). Fast and robust: Task sampling with posterior and diversity synergies for adaptive decision-makers in randomized environments. arXiv: 2504.19139."},{"key":"10.1016\/j.eswa.2026.133316_bib0036","unstructured":"Reddi, S. J., Ramdas, A., P\u00f3czos, B., Singh, A., & Wasserman, L. (2014). Kernel MMD, the median heuristic and distance correlation in high dimensions. arXiv: 1406.2083."},{"key":"10.1016\/j.eswa.2026.133316_bib0037","unstructured":"Rudner, T. G. J., Lu, C., Osborne, M. A., Gal, Y., & Teh, Y. (2021). On pathologies in KL-regularized reinforcement learning from expert demonstrations. (pp. 28376\u201328389). (vol. 34). arXiv:2212.13936."},{"key":"10.1016\/j.eswa.2026.133316_bib0038","unstructured":"Schaul, T. (2015). Prioritized experience replay. arXiv: 1511.05952."},{"key":"10.1016\/j.eswa.2026.133316_bib0039","unstructured":"Schrittwieser, J., Hubert, T., Mandhane, A., Barekatain, M., Antonoglou, I., & Silver, D. (2021). Online and offline reinforcement learning by planning with a learned model. (pp. 27580\u201327591). (vol. 34). arXiv:2104.06294."},{"key":"10.1016\/j.eswa.2026.133316_bib0040","unstructured":"Silver, T., Allen, K., Tenenbaum, J., & Kaelbling, L. (2018). Residual policy learning. arXiv: 1812.06298."},{"issue":"1","key":"10.1016\/j.eswa.2026.133316_bib0041","first-page":"1","article-title":"An introduction to the bootstrap","volume":"57","author":"Tibshirani","year":"1993","journal-title":"Monographs on Statistics and Applied Probability"},{"key":"10.1016\/j.eswa.2026.133316_bib0042","series-title":"2012\u202fIEEE\/RSJ International conference on intelligent robots and systems","first-page":"5026","article-title":"MuJoCo: A physics engine for model-based control","author":"Todorov","year":"2012"},{"key":"10.1016\/j.eswa.2026.133316_bib0043","series-title":"International conference on machine learning","first-page":"23055","article-title":"Model-based meta reinforcement learning using graph structured surrogate models and amortized policy search","author":"Wang","year":"2022"},{"key":"10.1016\/j.eswa.2026.133316_bib0044","doi-asserted-by":"crossref","unstructured":"Wang, Q., Xiao, Z., Mao, Y., Qu, Y., Shen, J., Lv, Y., & Ji, X. (2025). Model predictive task sampling for efficient and robust adaptation. arXiv: 2501.11039.","DOI":"10.21203\/rs.3.rs-6700167\/v1"},{"key":"10.1016\/j.eswa.2026.133316_bib0045","doi-asserted-by":"crossref","unstructured":"Wang, S., Yang, Q., Gao, J., Lin, M., Chen, H., Wu, L., Jia, N., Song, S., & Huang, G. (2023). Train once, get a family: State-adaptive balances for offline-to-online reinforcement learning. (vol. 36). arXiv:2310.17966.","DOI":"10.52202\/075280-2039"},{"key":"10.1016\/j.eswa.2026.133316_bib0046","unstructured":"Wang, Z., Hunt, J. J., & Zhou, M. (2022). Diffusion policies as an expressive policy class for offline reinforcement learning. arXiv: 2208.06193."},{"key":"10.1016\/j.eswa.2026.133316_bib0047","series-title":"IJCAI","first-page":"5739","article-title":"Towards sample efficient reinforcement learning","author":"Yu","year":"2018"},{"key":"10.1016\/j.eswa.2026.133316_bib0048","series-title":"International conference on machine learning","first-page":"40452","article-title":"Actor-critic alignment for offline-to-online reinforcement learning","author":"Yu","year":"2023"},{"key":"10.1016\/j.eswa.2026.133316_bib0049","unstructured":"Zhang, H., Xu, W., & Yu, H. (2023). Policy expansion for bridging offline-to-online reinforcement learning. arXiv: 2302.00935."},{"key":"10.1016\/j.eswa.2026.133316_bib0050","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"16908","article-title":"A perspective of q-value estimation on offline-to-online reinforcement learning","volume":"vol. 38","author":"Zhang","year":"2024"},{"key":"10.1016\/j.eswa.2026.133316_bib0051","series-title":"ICML workshop on new frontiers in learning, control, and dynamical systems","article-title":"Improving offline-to-online reinforcement learning with q-ensembles","author":"Zhao","year":"2023"},{"key":"10.1016\/j.eswa.2026.133316_bib0052","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Boney, R., Ilin, A., Kannala, J., & Pajarinen, J. (2022). Adaptive behavior cloning regularization for stable offline-to-online reinforcement learning. arXiv: 2210.13846.","DOI":"10.14428\/esann\/2022.ES2022-110"},{"key":"10.1016\/j.eswa.2026.133316_bib0053","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"11372","article-title":"Adaptive policy learning for offline-to-online reinforcement learning","volume":"vol. 37","author":"Zheng","year":"2023"},{"key":"10.1016\/j.eswa.2026.133316_bib0054","series-title":"International conference on machine learning","first-page":"27042","article-title":"Online decision transformer","author":"Zheng","year":"2022"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426022256?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426022256?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T07:42:15Z","timestamp":1790322135000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426022256"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":54,"alternative-id":["S0957417426022256"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133316","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Proud: Sample-efficient offline-to-online reinforcement learning via prioritized diffusion model","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133316","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"133316"}}