{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:18:52Z","timestamp":1780053532957,"version":"3.54.0"},"reference-count":80,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62576364"],"award-info":[{"award-number":["62576364"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NTU RSR"},{"name":"NTU RSR"},{"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"}]},{"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"}]},{"name":"Key R&D Project of Jilin Province","award":["20240304200SF"],"award-info":[{"award-number":["20240304200SF"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tpami.2026.3652193","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:00:30Z","timestamp":1768255230000},"page":"5346-5356","source":"Crossref","is-referenced-by-count":1,"title":["Instructed Diffuser With Temporal Condition Guidance for Offline Reinforcement Learning"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8658-9447","authenticated-orcid":false,"given":"Jifeng","family":"Hu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1137-9939","authenticated-orcid":false,"given":"Yanchao","family":"Sun","sequence":"additional","affiliation":[{"name":"University of Maryland, College Park, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5387-7904","authenticated-orcid":false,"given":"Sili","family":"Huang","sequence":"additional","affiliation":[{"name":"Minzu University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9304-5405","authenticated-orcid":false,"given":"Siyuan","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7835-9556","authenticated-orcid":false,"given":"Hechang","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5659-3464","authenticated-orcid":false,"given":"Li","family":"Shen","sequence":"additional","affiliation":[{"name":"Shenzhen Campus of Sun Yat-sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2697-8093","authenticated-orcid":false,"given":"Yi","family":"Chang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho","year":"2020"},{"key":"ref2","first-page":"11918","article-title":"Generative modeling by estimating gradients of the data distribution","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Song","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"ref4","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref7","first-page":"9902","article-title":"Planning with diffusion for flexible behavior synthesis","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Janner"},{"key":"ref8","first-page":"29598","article-title":"Is conditional generative modeling all you need for decision-making?","volume-title":"Proc. 11th Proc. Int. Conf. Learn. Representations","author":"Ajay"},{"key":"ref9","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"2020","author":"Kumar"},{"key":"ref10","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen","year":"2021"},{"key":"ref11","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bellemare","year":"2017"},{"key":"ref12","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020"},{"key":"ref13","article-title":"Offline reinforcement learning with implicit q-learning","author":"Kostrikov","year":"2021"},{"key":"ref14","first-page":"7513","article-title":"Offline RL policies should be trained to be adaptive","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ghosh","year":"2022"},{"key":"ref15","first-page":"7436","article-title":"Uncertainty-based offline reinforcement learning with diversified q-ensemble","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"2021","author":"An"},{"key":"ref16","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proc. 40th Int. Conf. Artif. Intell. Statistics. JMLR Workshop Conf.","author":"Ross","year":"2011"},{"key":"ref17","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"2021","author":"Fujimoto"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20783"},{"key":"ref19","first-page":"6683","article-title":"Bellman-consistent pessimism for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"2021","author":"Xie"},{"key":"ref20","first-page":"11784","article-title":"Stabilizing off-policy q-learning via bootstrapping error reduction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Kumar","year":"2019"},{"key":"ref21","first-page":"21810","article-title":"Morel: Model-based offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"2020","author":"Kidambi"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.2307\/jj.20206644.79"},{"key":"ref23","first-page":"1154","article-title":"Offline reinforcement learning from images with latent space models","volume-title":"Proc. Learn. Dyn. Control","author":"Rafailov","year":"2021"},{"key":"ref24","first-page":"1273","article-title":"Offline reinforcement learning as one big sequence modeling problem","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"2021","author":"Janner"},{"key":"ref25","article-title":"SaFormer: A Conditional sequence modeling approach to offline safe reinforcement learning","author":"Zhang","year":"2023"},{"key":"ref26","article-title":"Generalized decision transformer for offline hindsight information matching","author":"Furuta","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2518"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3408271"},{"key":"ref29","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein","year":"2015"},{"key":"ref30","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref32","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"2021","author":"Dhariwal"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00037"},{"key":"ref34","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3758\/s13423-018-1554-2"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref37","first-page":"6494","article-title":"Efficient planning with latent diffusion","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Li"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01425"},{"key":"ref39","first-page":"26790","article-title":"Diffusion policies as an expressive policy class for offline reinforcement learning","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref40","first-page":"9156","article-title":"Learning universal policies via text-guided video generation","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Du"},{"key":"ref41","first-page":"26087","article-title":"MetaDiffuser: Diffusion model as conditional planner for offline meta-RL","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ni","year":"2023"},{"key":"ref42","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hafner","year":"2019"},{"key":"ref43","first-page":"10711","article-title":"Mastering Atari with discrete world models","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Hafner"},{"key":"ref44","first-page":"9654","article-title":"Transformers are sample-efficient world models","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Micheli"},{"key":"ref45","article-title":"Certifiably robust policy learning against adversarial communication in multi-agent systems","author":"Sun","year":"2022"},{"key":"ref46","first-page":"29723","article-title":"SMART: Self-supervised multi-task pretraining with control transformers","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Sun"},{"key":"ref47","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"key":"ref48","article-title":"D4RL: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020"},{"key":"ref49","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2019"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"ref51","first-page":"25969","article-title":"Efficient planning in a compact latent action space","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref52","first-page":"20035","article-title":"Hierarchical diffusion for offline decision making","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref53","first-page":"53729","article-title":"Simple hierarchical planning with diffusion","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3895"},{"key":"ref55","first-page":"28597","article-title":"DiffStitch: Boosting offline reinforcement learning with diffusion-based trajectory stitching","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref56","article-title":"BiTrajDiff: Bidirectional trajectory generation with diffusion models for offline reinforcement learning","author":"Qing","year":"2025"},{"key":"ref57","article-title":"Extendable long-horizon planning via hierarchical multiscale diffusion","author":"Chen","year":"2025"},{"key":"ref58","first-page":"602","article-title":"RTDiff: Reverse trajectory synthesis via diffusion for offline reinforcement learning","volume-title":"Proc. 13th Proc. Int. Conf. Learn. Representations","author":"Yang","year":"2025"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.3233\/faia230618"},{"key":"ref60","article-title":"Augmenting offline reinforcement learning with state-only interactions","author":"Li","year":"2024"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2009"},{"key":"ref62","first-page":"32211","article-title":"Consistency models","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Song"},{"key":"ref63","article-title":"Planning with consistency models for model-based offline reinforcement learning","author":"Wang","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref64","first-page":"43337","article-title":"Consistency models as a rich and efficient policy class for reinforcement learning","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Ding"},{"key":"ref65","article-title":"Consistency trajectory planning: High-quality and efficient trajectory optimization for offline model-based reinforcement learning","author":"Wang","year":"2025"},{"key":"ref66","article-title":"LLama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref67","article-title":"Tackling continual offline RL through selective weights activation on aligned spaces","volume-title":"Proc. 39th Annu. Conf. Neural Inf. Process. Syst.","author":"Hu","year":"2025"},{"key":"ref68","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25549-6_5"},{"key":"ref70","first-page":"22419","article-title":"Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"2021","author":"Wu"},{"key":"ref71","first-page":"13014","article-title":"MICN: Multi-scale local and global context modeling for long-term series forecasting","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Wang","year":"2023"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref73","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref74","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018","journal-title":"OpenAI"},{"key":"ref75","article-title":"All are worth words: A ViT backbone for score. Based diffusion models","volume-title":"Proc. NeurIPS 2022 Workshop Score. Based Methods","author":"Bao"},{"key":"ref76","article-title":"Analytic energy-guided policy optimization for offline reinforcement learning","volume-title":"Proc. 39th Annu. Conf. Neural Inf. Process. Syst.","author":"Hu"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.1.1"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref80","first-page":"1282","article-title":"Quantifying generalization in reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cobbe","year":"2019"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11474534\/11342301.pdf?arnumber=11342301","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T19:56:24Z","timestamp":1775505384000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11342301\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":80,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3652193","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}