{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T11:04:27Z","timestamp":1768302267752,"version":"3.49.0"},"reference-count":58,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci. China Inf. Sci."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1007\/s11432-024-4545-1","type":"journal-article","created":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T03:26:53Z","timestamp":1768274813000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Prompt tuning with preference ranking for few-shot pre-trained decision transformer"],"prefix":"10.1007","volume":"69","author":[{"given":"Shengchao","family":"Hu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ya","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,4]]},"reference":[{"key":"4545_CR1","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown T, Mann B, Ryder N, et al. Language models are few-shot learners. Adv Neural Inform Process Syst, 2020, 33: 1877\u20131901","journal-title":"Adv Neural Inform Process Syst"},{"key":"4545_CR2","unstructured":"Devlin J, Chang M W, Lee K, et al. BERT: pre-training of deep bidirectional transformers for language understanding. ArXiv:1810.04805"},{"key":"4545_CR3","first-page":"27921","volume":"35","author":"K H Lee","year":"2022","unstructured":"Lee K H, Nachum O, Yang M S, et al. Multi-game decision transformers. Adv Neural Inform Process Syst, 2022, 35: 27921\u201327936","journal-title":"Adv Neural Inform Process Syst"},{"key":"4545_CR4","unstructured":"Reed S, Zolna K, Parisotto E, et al. A generalist agent. ArXiv:2205.06175"},{"key":"4545_CR5","unstructured":"Li X L, Liang P. Prefix-tuning: optimizing continuous prompts for generation. ArXiv:2101.00190"},{"key":"4545_CR6","unstructured":"Shin T, Razeghi Y, Logan IV R L, et al. Autoprompt: eliciting knowledge from language models with automatically generated prompts. ArXiv:2010.15980"},{"key":"4545_CR7","unstructured":"Liu X, Zheng Y, Du Z, et al. Gpt understands, too. ArXiv:2103.10385"},{"key":"4545_CR8","unstructured":"Lester B, Al-Rfou R, Constant N. The power of scale for parameter-efficient prompt tuning. ArXiv:2104.08691"},{"key":"4545_CR9","unstructured":"Zhong Z, Friedman D, Chen D. Factual probing is [MASK]: learning vs. learning to recall. ArXiv:2104.05240"},{"key":"4545_CR10","first-page":"7780","volume-title":"Proceedings of the International Conference on Machine Learning","author":"E Mitchell","year":"2021","unstructured":"Mitchell E, Rafailov R, Peng X B, et al. Offline meta-reinforcement learning with advantage weighting. In: Proceedings of the International Conference on Machine Learning, 2021. 7780\u20137791"},{"key":"4545_CR11","unstructured":"Nichol A, Achiam J, Schulman J. On first-order meta-learning algorithms. ArXiv:1803.02999"},{"key":"4545_CR12","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"A Rajeswaran","year":"2019","unstructured":"Rajeswaran A, Finn C, Kakade S M, et al. Meta-learning with implicit gradients. In: Proceedings of Advances in Neural Information Processing Systems, 2019"},{"key":"4545_CR13","first-page":"24631","volume-title":"Proceedings of the International Conference on Machine Learning","author":"M Xu","year":"2022","unstructured":"Xu M, Shen Y, Zhang S, et al. Prompting decision transformer for few-shot policy generalization. In: Proceedings of the International Conference on Machine Learning, 2022. 24631\u201324645"},{"key":"4545_CR14","unstructured":"Levine S, Kumar A, Tucker G, et al. Offline reinforcement learning: tutorial, review, and perspectives on open problems. ArXiv:2005.01643"},{"key":"4545_CR15","first-page":"2052","volume-title":"Proceedings of the International Conference on Machine Learning","author":"S Fujimoto","year":"2019","unstructured":"Fujimoto S, Meger D, Precup D. Off-policy deep reinforcement learning without exploration. In: Proceedings of the International Conference on Machine Learning, 2019. 2052\u20132062"},{"key":"4545_CR16","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"A Kumar","year":"2019","unstructured":"Kumar A, Fu J, Soh M, et al. Stabilizing off-policy q-learning via bootstrapping error reduction. In: Proceedings of Advances in Neural Information Processing Systems, 2019"},{"key":"4545_CR17","first-page":"1179","volume":"33","author":"A Kumar","year":"2020","unstructured":"Kumar A, Zhou A, Tucker G, et al. Conservative Q-learning for offline reinforcement learning. Adv Neural Inform Process Syst, 2020, 33: 1179\u20131191","journal-title":"Adv Neural Inform Process Syst"},{"key":"4545_CR18","first-page":"21810","volume":"33","author":"R Kidambi","year":"2020","unstructured":"Kidambi R, Rajeswaran A, Netrapalli P, et al. MoReL: model-based offline reinforcement learning. Adv Neural Inform Process Syst, 2020, 33: 21810\u201321823","journal-title":"Adv Neural Inform Process Syst"},{"key":"4545_CR19","first-page":"14129","volume":"33","author":"T Yu","year":"2020","unstructured":"Yu T, Thomas G, Yu L, et al. MOPO: model-based offline policy optimization. Adv Neural Inform Process Syst, 2020, 33: 14129\u201314142","journal-title":"Adv Neural Inform Process Syst"},{"key":"4545_CR20","unstructured":"Hu S, Shen L, Zhang Y, et al. Graph decision transformer. ArXiv:2303.03747"},{"key":"4545_CR21","first-page":"19182","volume-title":"Proceedings of the International Conference on Machine Learning","author":"S Hu","year":"2024","unstructured":"Hu S, Fan Z, Shen L, et al. HarmoDT: harmony multi-task decision transformer for offline reinforcement learning. In: Proceedings of the International Conference on Machine Learning, 2024. 19182\u201319197"},{"key":"4545_CR22","first-page":"19165","volume-title":"Proceedings of the International Conference on Machine Learning","author":"S Hu","year":"2024","unstructured":"Hu S, Fan Z, Huang C, et al. Q-value regularized transformer for offline reinforcement learning. In: Proceedings of the International Conference on Machine Learning, 2024. 19165\u201319181"},{"key":"4545_CR23","doi-asserted-by":"publisher","first-page":"51474","DOI":"10.52202\/079017-1629","volume":"37","author":"Y Dai","year":"2024","unstructured":"Dai Y, Ma O, Zhang L, et al. Is Mamba compatible with trajectory optimization in offline reinforcement learning? Adv Neural Inform Process Syst, 2024, 37: 51474\u201351502","journal-title":"Adv Neural Inform Process Syst"},{"key":"4545_CR24","doi-asserted-by":"publisher","first-page":"8580","DOI":"10.1109\/TPAMI.2024.3408271","volume":"46","author":"S Hu","year":"2024","unstructured":"Hu S, Shen L, Zhang Y, et al. On transforming reinforcement learning with transformers: the development trajectory. Proc IEEE Trans Pattern Anal Mach Intell, 2024, 46: 8580\u20138599","journal-title":"Proc IEEE Trans Pattern Anal Mach Intell"},{"key":"4545_CR25","unstructured":"Li W, Luo H, Lin Z, et al. A survey on transformers in reinforcement learning. ArXiv:2301.03044"},{"key":"4545_CR26","doi-asserted-by":"publisher","first-page":"4419","DOI":"10.1109\/TIP.2024.3434475","volume":"33","author":"X Wang","year":"2024","unstructured":"Wang X, Ji Z, Yu Y, et al. Model attention expansion for few-shot class-incremental learning. Proc IEEE Trans Image Process, 2024, 33: 4419\u20134431","journal-title":"Proc IEEE Trans Image Process"},{"key":"4545_CR27","unstructured":"Liu J, Ji Z, Pang Y, et al. NTK-guided few-shot class incremental learning. ArXiv:2403.12486"},{"key":"4545_CR28","first-page":"6197","volume":"33","author":"J Li","year":"2020","unstructured":"Li J, Vuong Q, Liu S, et al. Multi-task batch reinforcement learning with metric learning. Adv Neural Inform Process Syst, 2020, 33: 6197\u20136210","journal-title":"Adv Neural Inform Process Syst"},{"key":"4545_CR29","first-page":"4607","volume":"34","author":"R Dorfman","year":"2021","unstructured":"Dorfman R, Shenfeld I, Tamar A. Offline meta reinforcement learning\u2013identifiability challenges and effective data collection strategies. Adv Neural Inform Process Syst, 2021, 34: 4607\u20134618","journal-title":"Adv Neural Inform Process Syst"},{"key":"4545_CR30","unstructured":"Zintgraf L, Shiarlis K, Igl M, et al. VariBAD: a very good method for Bayes-adaptive deep RL via meta-learning. ArXiv:1910.08348"},{"key":"4545_CR31","first-page":"1126","volume-title":"Proceedings of the International Conference on Machine Learning","author":"C Finn","year":"2017","unstructured":"Finn C, Abbeel P, Levine S. Model-agnostic meta-learning for fast adaptation of deep networks. In: Proceedings of the International Conference on Machine Learning, 2017. 1126\u20131135"},{"key":"4545_CR32","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou K, Yang J, Loy C C, et al. Learning to prompt for vision-language models. Int J Comput Vis, 2022, 130: 2337\u20132348","journal-title":"Int J Comput Vis"},{"key":"4545_CR33","first-page":"16816","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"K Zhou","year":"2022","unstructured":"Zhou K, Yang J, Loy C C, et al. Conditional prompt learning for vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022. 16816\u201316825"},{"key":"4545_CR34","first-page":"20841","volume-title":"Proceedings of the International Conference on Machine Learning","author":"T Sun","year":"2022","unstructured":"Sun T, Shao Y, Qian H, et al. Black-box tuning for language-model-as-a-service. In: Proceedings of the International Conference on Machine Learning, 2022. 20841\u201320855"},{"key":"4545_CR35","unstructured":"Prasad A, Hase P, Zhou X, et al. GrIPS: gradient-free, edit-based instruction search for prompting large language models. ArXiv:2203.07281"},{"key":"4545_CR36","volume-title":"Reinforcement Learning: an Introduction","author":"R S Sutton","year":"2018","unstructured":"Sutton R S, Barto A G. Reinforcement Learning: an Introduction. Cambridge: MIT Press, 2018"},{"key":"4545_CR37","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"A Vaswani","year":"2017","unstructured":"Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need. In: Proceedings of Advances in Neural Information Processing Systems, 2017"},{"key":"4545_CR38","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, et al. An image is worth 16 \u00d7 16 words: transformers for image recognition at scale. ArXiv:2010.11929"},{"key":"4545_CR39","first-page":"1","volume":"55","author":"P Liu","year":"2023","unstructured":"Liu P, Yuan W, Fu J, et al. Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing. ACM Comput Sur, 2023, 55: 1\u201335","journal-title":"ACM Comput Sur"},{"key":"4545_CR40","first-page":"1011","volume-title":"Proceedings of the Conference on Robot Learning","author":"V Jain","year":"2023","unstructured":"Jain V, Lin Y, Undersander E, et al. Transformers are adaptable task planners. In: Proceedings of the Conference on Robot Learning, 2023. 1011\u20131037"},{"key":"4545_CR41","first-page":"15084","volume":"34","author":"L Chen","year":"2021","unstructured":"Chen L, Lu K, Rajeswaran A, et al. Decision transformer: reinforcement learning via sequence modeling. Adv Neural Inform Process Syst, 2021, 34: 15084\u201315097","journal-title":"Adv Neural Inform Process Syst"},{"key":"4545_CR42","unstructured":"Frazier P I. A tutorial on Bayesian optimization. ArXiv:1807.02811"},{"key":"4545_CR43","doi-asserted-by":"publisher","first-page":"527","DOI":"10.1007\/s10208-015-9296-2","volume":"17","author":"Y Nesterov","year":"2017","unstructured":"Nesterov Y, Spokoiny V. Random Gradient-Free Minimization of Convex Functions. Found Comput Math, 2017, 17: 527\u2013566","journal-title":"Found Comput Math"},{"key":"4545_CR44","unstructured":"Loshchilov I, Hutter F. CMA-ES for hyperparameter optimization of deep neural networks. ArXiv:1604.07269"},{"key":"4545_CR45","unstructured":"Bai Y, Jones A, Ndousse K, et al. Training a helpful and harmless assistant with reinforcement learning from human feedback. ArXiv:2204.05862"},{"key":"4545_CR46","first-page":"27730","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang L, Wu J, Jiang X, et al. Training language models to follow instructions with human feedback. Adv Neural Inform Process Syst, 2022, 35: 27730\u201327744","journal-title":"Adv Neural Inform Process Syst"},{"key":"4545_CR47","doi-asserted-by":"publisher","first-page":"242","DOI":"10.1016\/j.acha.2022.03.003","volume":"60","author":"H Q Cai","year":"2022","unstructured":"Cai H Q, McKenzie D, Yin W, et al. A one-bit, comparison-based gradient estimator. Appl Comput Harmon Anal, 2022, 60: 242\u2013266","journal-title":"Appl Comput Harmon Anal"},{"key":"4545_CR48","doi-asserted-by":"publisher","first-page":"2726","DOI":"10.1137\/19M1244378","volume":"30","author":"E H Bergou","year":"2020","unstructured":"Bergou E H, Gorbunov E, Richt\u00e1rik P. Stochastic three points method for unconstrained smooth minimization. SIAM J Optim, 2020, 30: 2726\u20132749","journal-title":"SIAM J Optim"},{"key":"4545_CR49","unstructured":"Tang Z, Rybin D, Chang T H. Zeroth-order optimization meets human feedback: provable learning via ranking oracles. ArXiv:2303.03751"},{"key":"4545_CR50","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139174084","volume-title":"Decisions with Multiple Objectives: Preferences and Value Tradeoffs","author":"R L Keeney","year":"1993","unstructured":"Keeney R L. Decisions with Multiple Objectives: Preferences and Value Tradeoffs. Cambridge: Cambridge University Press, 1993"},{"key":"4545_CR51","first-page":"1356","volume-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics","author":"Y Wang","year":"2018","unstructured":"Wang Y, Du S, Balakrishnan S, et al. Stochastic zeroth-order optimization in high dimensions. In: Proceedings of the International Conference on Artificial Intelligence and Statistics, 2018. 1356\u20131365"},{"key":"4545_CR52","unstructured":"Rothfuss J, Lee D, Clavera I, et al. ProMP: proximal meta-policy search. ArXiv:1810.06784"},{"key":"4545_CR53","first-page":"1094","volume-title":"Proceedings of the Conference on Robot Learning","author":"T Yu","year":"2020","unstructured":"Yu T, Quillen D, He Z, et al. Meta-world: a benchmark and evaluation for multi-task and meta reinforcement learning. In: Proceedings of the Conference on Robot Learning, 2020. 1094\u20131100"},{"key":"4545_CR54","first-page":"1861","volume-title":"Proceedings of the International Conference on Machine Learning","author":"T Haarnoja","year":"2018","unstructured":"Haarnoja T, Zhou A, Abbeel P, et al. Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: Proceedings of the International Conference on Machine Learning, 2018. 1861\u20131870"},{"key":"4545_CR55","first-page":"1587","volume-title":"Proceedings of the International Conference on Machine Learning","author":"S Fujimoto","year":"2018","unstructured":"Fujimoto S, Hoof H, Meger D. Addressing function approximation error in actor-critic methods. In: Proceedings of the International Conference on Machine Learning, 2018. 1587\u20131596"},{"key":"4545_CR56","unstructured":"Loshchilov I, Hutter F, et al. Fixing weight decay regularization in Adam. ArXiv:1711.05101"},{"key":"4545_CR57","unstructured":"Xu M, Lu Y, Shen Y, et al. Hyper-decision transformer for efficient online policy adaptation. ArXiv:2304.08487"},{"key":"4545_CR58","unstructured":"Gu Y, Han X, Liu Z, et al. PPT: pre-trained prompt tuning for few-shot learning. ArXiv:2109.04332"}],"container-title":["Science China Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-024-4545-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11432-024-4545-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-024-4545-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T03:27:09Z","timestamp":1768274829000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11432-024-4545-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":58,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["4545"],"URL":"https:\/\/doi.org\/10.1007\/s11432-024-4545-1","relation":{},"ISSN":["1674-733X","1869-1919"],"issn-type":[{"value":"1674-733X","type":"print"},{"value":"1869-1919","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"17 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 January 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 March 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 January 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"112105"}}