{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T21:02:22Z","timestamp":1784408542119,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":25,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819233809","type":"print"},{"value":"9789819233816","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"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":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-981-92-3381-6_19","type":"book-chapter","created":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T20:15:32Z","timestamp":1784405732000},"page":"229-241","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["P2DT: Prompt Prototype Decision Transformer for Scalable Offline Multi-task Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Donghui","family":"Ma","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ye","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"19_CR1","unstructured":"Levine, S., Kumar, A., Tucker, G., Fu, J.: Offline reinforcement learning: tutorial, review, and perspectives on Open Problems. arXiv preprint https:\/\/arxiv.org\/abs\/2005.01643 (2020)"},{"issue":"8","key":"19_CR2","doi-asserted-by":"publisher","first-page":"10237","DOI":"10.1109\/TNNLS.2023.3250269","volume":"35","author":"RF Prudencio","year":"2024","unstructured":"Prudencio, R.F., Maximo, M.R.O.A., Colombini, E.L.: A survey on offline reinforcement learning: taxonomy, review, and open problems. IEEE Trans. Neural Netw. Learn. Syst. 35(8), 10237\u201310257 (2024)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"19_CR3","unstructured":"Crawshaw, M.: Multi-task learning with deep neural networks: a survey. arXiv preprint https:\/\/arxiv.org\/abs\/2009.09796 (2020)"},{"key":"19_CR4","first-page":"4496","volume":"30","author":"YW Teh","year":"2017","unstructured":"Teh, Y.W., et al.: Distral: robust multitask reinforcement learning. Adv. Neural Inf. Process. Syst. 30, 4496\u20134506 (2017)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"19_CR5","first-page":"4767","volume":"33","author":"R Yang","year":"2020","unstructured":"Yang, R., Xu, H., Wu, Y., Wang, X.: Multi-task reinforcement learning with soft modularization. Adv. Neural Inf. Process. Syst. 33, 4767\u20134777 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"19_CR6","first-page":"11501","volume":"34","author":"T Yu","year":"2021","unstructured":"Yu, T., Kumar, A., Chebotar, Y., Hausman, K., Levine, S., Finn, C.: Conservative data sharing for multi-task offline reinforcement learning. Adv. Neural Inf. Process. Syst. 34, 11501\u201311516 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"19_CR7","first-page":"5824","volume":"33","author":"T Yu","year":"2020","unstructured":"Yu, T., Kumar, S., Gupta, A., Levine, S., Hausman, K., Finn, C.: Gradient surgery for multi-task learning. Adv. Neural Inf. Process. Syst. 33, 5824\u20135836 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"19_CR8","first-page":"525","volume":"31","author":"O Sener","year":"2018","unstructured":"Sener, O., Koltun, V.: Multi-task learning as multi-objective optimization. Adv. Neural Inf. Process. Syst. 31, 525\u2013536 (2018)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"19_CR9","unstructured":"Sodhani, S., Zhang, A., Pineau, J.: Multi-task reinforcement learning with context-based representations. In: Proceedings of the 38th International Conference on Machine Learning (ICML). Proceedings of Machine Learning Research, vol. 139, pp. 9767\u20139779 (2021)"},{"key":"19_CR10","first-page":"6197","volume":"33","author":"J Li","year":"2020","unstructured":"Li, J., et al.: Multi-task batch reinforcement learning with metric learning. Adv. Neural Inf. Process. Syst. 33, 6197\u20136210 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"19_CR11","first-page":"15084","volume":"34","author":"L Chen","year":"2021","unstructured":"Chen, L., et al.: Decision transformer: reinforcement learning via sequence modeling. Adv. Neural Inf. Process. Syst. 34, 15084\u201315097 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"19_CR12","first-page":"5998","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30, 5998\u20136008 (2017)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"19_CR13","first-page":"1273","volume":"34","author":"M Janner","year":"2021","unstructured":"Janner, M., Li, Q., Levine, S.: Offline reinforcement learning as one big sequence modeling problem. Adv. Neural Inf. Process. Syst. 34, 1273\u20131286 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"19_CR14","unstructured":"Chebotar, Y., et al.: Q-Transformer: scalable offline reinforcement learning via autoregressive Q-functions. In: Proceedings of the Conference on Robot Learning (CoRL). Proceedings of Machine Learning Research, vol. 229, pp. 3909\u20133928 (2023)"},{"key":"19_CR15","unstructured":"Xu, M., et al.: Prompting decision transformer for few-shot policy generalization. In: Proceedings of the 39th International Conference on Machine Learning (ICML). Proceedings of Machine Learning Research, vol. 162, pp. 24631\u201324645 (2022)"},{"key":"19_CR16","doi-asserted-by":"publisher","first-page":"64896","DOI":"10.52202\/075280-2832","volume":"36","author":"H He","year":"2023","unstructured":"He, H., et al.: Diffusion model is an effective planner and data synthesizer for multi-task reinforcement learning. Adv. Neural Inf. Process. Syst. 36, 64896\u201364917 (2023)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"19_CR17","unstructured":"Hu, S., Fan, Z., Shen, L., Zhang, Y., Wang, Y., Tao, D.: HarmoDT: harmony multi-task decision transformer for offline reinforcement learning. In: Proceedings of the 41st International Conference on Machine Learning (ICML). Proceedings of Machine Learning Research, vol. 235, pp. 19182\u201319197 (2024)"},{"key":"19_CR18","doi-asserted-by":"publisher","first-page":"21495","DOI":"10.52202\/068431-1562","volume":"35","author":"L Sun","year":"2022","unstructured":"Sun, L., Zhang, H., Xu, W., Tomizuka, M.: PaCo: parameter-compositional multi-task reinforcement learning. Adv. Neural Inf. Process. Syst. 35, 21495\u201321507 (2022)","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"31","key":"19_CR19","first-page":"26462","volume":"40","author":"S Wang","year":"2026","unstructured":"Wang, S., et al.: Soft conflict-resolution decision transformer for offline multi-task reinforcement learning. Proc. AAAI Conf. Artif. Intell. 40(31), 26462\u201326470 (2026)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"19_CR20","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: Proceedings of the 37th International Conference on Machine Learning (ICML). Proceedings of Machine Learning Research, vol. 119, pp. 1597\u20131607 (2020)"},{"key":"19_CR21","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9726\u20139735 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"19_CR22","first-page":"18661","volume":"33","author":"P Khosla","year":"2020","unstructured":"Khosla, P., et al.: Supervised contrastive learning. Adv. Neural Inf. Process. Syst. 33, 18661\u201318673 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"19_CR23","first-page":"4077","volume":"30","author":"J Snell","year":"2017","unstructured":"Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. Adv. Neural Inf. Process. Syst. 30, 4077\u20134087 (2017)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"19_CR24","unstructured":"Yu, T. et al.: Meta-World: a benchmark and evaluation for multi-task and meta reinforcement learning. In: Proceedings of the Conference on Robot Learning (CoRL). Proceedings of Machine Learning Research, vol. 100, pp. 1094\u20131100 (2020)"},{"key":"19_CR25","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: Proceedings of the 35th International Conference on Machine Learning (ICML). Proceedings of Machine Learning Research, vol. 80, pp. 1861\u20131870 (2018)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3381-6_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T20:15:36Z","timestamp":1784405736000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3381-6_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"ISBN":["9789819233809","9789819233816"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3381-6_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"19 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}