{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T21:27:31Z","timestamp":1770845251481,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,5]]},"DOI":"10.1109\/smc58881.2025.11342806","type":"proceedings-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:54:44Z","timestamp":1769633684000},"page":"4171-4175","source":"Crossref","is-referenced-by-count":0,"title":["PDD: Planning Offline Meta-RL with Prompt Decision Diffuser"],"prefix":"10.1109","author":[{"given":"Shilin","family":"Zhang","sequence":"first","affiliation":[{"name":"Nanjing University,Department of Control Science and Intelligent Engineering,Nanjing,China"}]},{"given":"Zican","family":"Hu","sequence":"additional","affiliation":[{"name":"Nanjing University,Department of Control Science and Intelligent Engineering,Nanjing,China"}]},{"given":"Wenhao","family":"Wu","sequence":"additional","affiliation":[{"name":"Nanjing University,Department of Control Science and Intelligent Engineering,Nanjing,China"}]},{"given":"Xinyi","family":"Xie","sequence":"additional","affiliation":[{"name":"Nanjing University,Department of Control Science and Intelligent Engineering,Nanjing,China"}]},{"given":"Jiangxiang","family":"Tang","sequence":"additional","affiliation":[{"name":"Nanjing University,Department of Control Science and Intelligent Engineering,Nanjing,China"}]},{"given":"Zhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanjing University,Department of Control Science and Intelligent Engineering,Nanjing,China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref2","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref3","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref4","first-page":"36 479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref5","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning. PmLR","author":"Radford"},{"key":"ref6","first-page":"27 921","article-title":"Multi-game decision transformers","volume":"35","author":"Lee","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","first-page":"38 231","article-title":"Learning to modulate pre-trained models in rl","volume":"36","author":"Schmied","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","first-page":"785","article-title":"Perceiver-actor: A multi-task transformer for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Shridhar"},{"key":"ref9","first-page":"7780","article-title":"Offline meta-reinforcement learning with advantage weighting","volume-title":"International Conference on Machine Learning","author":"Mitchell"},{"key":"ref10","first-page":"17 811","article-title":"Offline meta-reinforcement learning with online self-supervision","volume-title":"International Conference on Machine Learning. Pmlr","author":"Pong"},{"key":"ref11","first-page":"4607","article-title":"Offline meta reinforcement learning-identifiability challenges and effective data collection strategies","volume":"34","author":"Dorfman","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","first-page":"9902","article-title":"Planning with diffusion for flexible behavior synthesis","volume-title":"International Conference on Machine Learning. PMLR","author":"Janner"},{"key":"ref13","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020"},{"key":"ref14","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume":"33","author":"Kumar","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref15","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"International conference on machine learning. PMLR","author":"Fujimoto"},{"key":"ref16","first-page":"21 810","article-title":"Morel: Model-based offline reinforcement learning","volume":"33","author":"Kidambi","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref17","article-title":"Focal: Efficient fully-offline meta-reinforcement learning via distance metric learning and behavior regularization","author":"Li","year":"2020"},{"key":"ref18","first-page":"25 747","article-title":"Robust task representations for offline meta-reinforcement learning via contrastive learning","volume-title":"International Conference on Machine Learning. PMLR","author":"Yuan"},{"key":"ref19","first-page":"64 896","article-title":"Diffusion model is an effective planner and data synthesizer for multi-task reinforcement learning","volume":"36","author":"He","year":"2023","journal-title":"Advances in neural information processing systems"},{"key":"ref20","first-page":"24 631","article-title":"Prompting decision transformer for few-shot policy generalization","volume-title":"international conference on machine learning. PMLR","author":"Xu"},{"key":"ref21","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref23","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021"},{"key":"ref24","article-title":"Is conditional generative modeling all you need for decision-making?","author":"Ajay","year":"2022"},{"key":"ref25","article-title":"Diffusion model-augmented behavioral cloning","author":"Chen","year":"2023"},{"key":"ref26","article-title":"Imitating human behaviour with diffusion models","author":"Pearce","year":"2023"},{"key":"ref27","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning. pmlr","author":"Sohl-Dickstein"},{"key":"ref28","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref29","first-page":"80 024","article-title":"Context shift reduction for offline meta-reinforcement learning","volume":"36","author":"Gao","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2408"}],"event":{"name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","location":"Vienna, Austria","start":{"date-parts":[[2025,10,5]]},"end":{"date-parts":[[2025,10,8]]}},"container-title":["2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11342430\/11342431\/11342806.pdf?arnumber=11342806","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:50:18Z","timestamp":1770843018000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11342806\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,5]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/smc58881.2025.11342806","relation":{},"subject":[],"published":{"date-parts":[[2025,10,5]]}}}