{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T23:52:14Z","timestamp":1782863534077,"version":"3.54.5"},"reference-count":45,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2025M771695"],"award-info":[{"award-number":["2025M771695"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004829","name":"Sichuan Province Department of Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004829","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100012542","name":"Sichuan Provincial Science and Technology Support Program","doi-asserted-by":"publisher","award":["2024ZDZX0015"],"award-info":[{"award-number":["2024ZDZX0015"]}],"id":[{"id":"10.13039\/100012542","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Engineering Applications of Artificial Intelligence"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.engappai.2026.115521","type":"journal-article","created":{"date-parts":[[2026,6,28]],"date-time":"2026-06-28T17:51:28Z","timestamp":1782669088000},"page":"115521","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"P3","title":["Flow-accelerated diffusion model for trajectory generation and optimization in offline reinforcement learning"],"prefix":"10.1016","volume":"181","author":[{"given":"He","family":"Diao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shan","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianglin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ping","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenyu","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2486-6776","authenticated-orcid":false,"given":"Bei","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.engappai.2026.115521_b1","unstructured":"Ajay, A., Du, Y., Gupta, A., Tenenbaum, J.B., Jaakkola, T.S., Agrawal, P., 2023. Is Conditional Generative Modeling all you need for Decision Making?. In: The Eleventh International Conference on Learning Representations."},{"issue":"209","key":"10.1016\/j.engappai.2026.115521_b2","first-page":"1","article-title":"Stochastic interpolants: A unifying framework for flows and diffusions","volume":"26","author":"Albergo","year":"2025","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.engappai.2026.115521_b3","unstructured":"Albergo, M.S., Vanden-Eijnden, E., 2023. BUILDING NORMALIZING FLOWS WITH STOCHASTIC INTERPOLANTS. In: 11th International Conference on Learning Representations. ICLR 2023."},{"issue":"3","key":"10.1016\/j.engappai.2026.115521_b4","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1016\/0304-4149(82)90051-5","article-title":"Reverse-time diffusion equation models","volume":"12","author":"Anderson","year":"1982","journal-title":"Stochastic Process. Appl."},{"key":"10.1016\/j.engappai.2026.115521_b5","article-title":"The option-critic architecture","volume":"vol. 31","author":"Bacon","year":"2017"},{"key":"10.1016\/j.engappai.2026.115521_b6","unstructured":"Chen, C., Deng, F., Kawaguchi, K., Gulcehre, C., Ahn, S., 2024. Simple Hierarchical Planning with Diffusion. In: The Twelfth International Conference on Learning Representations."},{"key":"10.1016\/j.engappai.2026.115521_b7","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume":"34","author":"Chen","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.115521_b8","article-title":"Diffusion policy: Visuomotor policy learning via action diffusion","author":"Chi","year":"2023","journal-title":"Int. J. Robot. Res."},{"key":"10.1016\/j.engappai.2026.115521_b9","article-title":"GATOC: Learning temporal abstraction with the option transition graph attention mechanism","author":"Diao","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.engappai.2026.115521_b10","doi-asserted-by":"crossref","first-page":"86899","DOI":"10.52202\/079017-2757","article-title":"Cleandiffuser: An easy-to-use modularized library for diffusion models in decision making","volume":"37","author":"Dong","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.115521_b11","series-title":"D4rl: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020"},{"key":"10.1016\/j.engappai.2026.115521_b12","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume":"34","author":"Fujimoto","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.115521_b13","series-title":"International Conference on Machine Learning","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","author":"Fujimoto","year":"2019"},{"key":"10.1016\/j.engappai.2026.115521_b14","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.115521_b15","series-title":"European Conference on Computer Vision","first-page":"1","article-title":"Diffusion models as optimizers for efficient planning in offline rl","author":"Huang","year":"2024"},{"key":"10.1016\/j.engappai.2026.115521_b16","series-title":"International Conference on Machine Learning","first-page":"9902","article-title":"Planning with diffusion for flexible behavior synthesis","author":"Janner","year":"2022"},{"key":"10.1016\/j.engappai.2026.115521_b17","first-page":"1273","article-title":"Offline reinforcement learning as one big sequence modeling problem","volume":"34","author":"Janner","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"2","key":"10.1016\/j.engappai.2026.115521_b18","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1007\/s10955-022-03026-x","article-title":"Stability of logarithmic Sobolev inequalities under a noncommutative change of measure","volume":"190","author":"Junge","year":"2023","journal-title":"J. Stat. Phys."},{"key":"10.1016\/j.engappai.2026.115521_b19","doi-asserted-by":"crossref","first-page":"67195","DOI":"10.52202\/075280-2937","article-title":"Efficient diffusion policies for offline reinforcement learning","volume":"36","author":"Kang","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.115521_b20","doi-asserted-by":"crossref","first-page":"26565","DOI":"10.52202\/068431-1926","article-title":"Elucidating the design space of diffusion-based generative models","volume":"35","author":"Karras","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.115521_b21","series-title":"International Conference on Algorithmic Learning Theory","first-page":"597","article-title":"On the computational complexity of self-attention","author":"Keles","year":"2023"},{"key":"10.1016\/j.engappai.2026.115521_b22","first-page":"13160","article-title":"Stitching sub-trajectories with conditional diffusion model for goal-conditioned offline RL","volume":"vol. 38","author":"Kim","year":"2024"},{"key":"10.1016\/j.engappai.2026.115521_b23","unstructured":"Kostrikov, I., Nair, A., Levine, S., 2021. Offline Reinforcement Learning with Implicit Q-Learning. In: Deep RL Workshop NeurIPS."},{"key":"10.1016\/j.engappai.2026.115521_b24","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume":"33","author":"Kumar","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.115521_b25","series-title":"International Conference on Machine Learning","first-page":"20035","article-title":"Hierarchical diffusion for offline decision making","author":"Li","year":"2023"},{"key":"10.1016\/j.engappai.2026.115521_b26","unstructured":"Liang, Z., Mu, Y., Ding, M., Ni, F., Tomizuka, M., Luo, P., 2023. AdaptDiffuser: diffusion models as adaptive self-evolving planners. In: Proceedings of the 40th International Conference on Machine Learning. pp. 20725\u201320745."},{"key":"10.1016\/j.engappai.2026.115521_b27","unstructured":"Lipman, Y., Chen, R.T., Ben-Hamu, H., Nickel, M., Le, M., 2023. Flow Matching for Generative Modeling. In: The Eleventh International Conference on Learning Representations."},{"key":"10.1016\/j.engappai.2026.115521_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112190","article-title":"DiffSkill: Improving reinforcement learning through diffusion-based skill denoiser for robotic manipulation","volume":"300","author":"Liu","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.engappai.2026.115521_b29","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.112108","article-title":"An uncertainty-aware safe-evolving reinforcement learning algorithm for decision-making and control in highway autonomous driving","volume":"161","author":"Lu","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.115521_b30","doi-asserted-by":"crossref","first-page":"98806","DOI":"10.52202\/079017-3136","article-title":"Diffusion-dice: In-sample diffusion guidance for offline reinforcement learning","volume":"37","author":"Mao","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"1\u20132","key":"10.1016\/j.engappai.2026.115521_b31","first-page":"1","article-title":"An algorithmic perspective on imitation learning","volume":"7","author":"Osa","year":"2018","journal-title":"Found. Trends\u00ae Robot."},{"key":"10.1016\/j.engappai.2026.115521_b32","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2023.111101","article-title":"Conservative network for offline reinforcement learning","volume":"282","author":"Peng","year":"2023","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.engappai.2026.115521_b33","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.108911","article-title":"A survey on reinforcement learning in aviation applications","volume":"136","author":"Razzaghi","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.115521_b34","series-title":"Fokker-planck equation","author":"Risken","year":"1996"},{"key":"10.1016\/j.engappai.2026.115521_b35","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"10.1016\/j.engappai.2026.115521_b36","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2021.104366","article-title":"Overcoming model bias for robust offline deep reinforcement learning","volume":"104","author":"Swazinna","year":"2021","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.115521_b37","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"7","key":"10.1016\/j.engappai.2026.115521_b38","doi-asserted-by":"crossref","first-page":"1661","DOI":"10.1162\/NECO_a_00142","article-title":"A connection between score matching and denoising autoencoders","volume":"23","author":"Vincent","year":"2011","journal-title":"Neural Comput."},{"key":"10.1016\/j.engappai.2026.115521_b39","series-title":"Consistency trajectory planning: High-quality and efficient trajectory optimization for offline model-based reinforcement learning","author":"Wang","year":"2025"},{"key":"10.1016\/j.engappai.2026.115521_b40","unstructured":"Wang, Z., Hunt, J.J., Zhou, M., 2023. Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning. In: The Eleventh International Conference on Learning Representations."},{"key":"10.1016\/j.engappai.2026.115521_b41","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.111828","article-title":"State slow feature softmax Q-value regularization for offline reinforcement learning","volume":"160","author":"Wu","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.115521_b42","series-title":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"2816","article-title":"Efficient trajectory forecasting and generation with conditional flow matching","author":"Ye","year":"2024"},{"key":"10.1016\/j.engappai.2026.115521_b43","unstructured":"Zhang, Y., Yan, Y., Schwing, A., Zhao, Z., 2025. Towards Hierarchical Rectified Flow. In: The Thirteenth International Conference on Learning Representations."},{"key":"10.1016\/j.engappai.2026.115521_b44","article-title":"MAD3PG: A framework for multi-agent deep denoising diffusion policy gradient optimization","author":"Zhong","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.engappai.2026.115521_b45","series-title":"International Conference on Machine Learning","first-page":"78903","article-title":"An error analysis of flow matching for deep generative modeling","author":"Zhou","year":"2025"}],"container-title":["Engineering Applications of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626018051?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626018051?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T23:02:16Z","timestamp":1782860536000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0952197626018051"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":45,"alternative-id":["S0952197626018051"],"URL":"https:\/\/doi.org\/10.1016\/j.engappai.2026.115521","relation":{},"ISSN":["0952-1976"],"issn-type":[{"value":"0952-1976","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Flow-accelerated diffusion model for trajectory generation and optimization in offline reinforcement learning","name":"articletitle","label":"Article Title"},{"value":"Engineering Applications of Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.engappai.2026.115521","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":"115521"}}