{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T20:28:27Z","timestamp":1785356907038,"version":"3.55.0"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T00:00:00Z","timestamp":1752796800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T00:00:00Z","timestamp":1752796800000},"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":["Artif Life Robotics"],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1007\/s10015-025-01036-y","type":"journal-article","created":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T18:05:34Z","timestamp":1752861934000},"page":"567-576","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Task-oriented adaptive learning of robot manipulation skills"],"prefix":"10.1007","volume":"30","author":[{"given":"Kexin","family":"Jin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guohui","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongcheng","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyu","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,18]]},"reference":[{"key":"1036_CR1","doi-asserted-by":"crossref","unstructured":"Liang J, Huang W, Xia F, et al (2023) Code as policies: Language model programs for embodied control. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 9493\u20139500","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"1036_CR2","unstructured":"Xu M, Huang P, Yu W, et al (2023) Creative robot tool use with large language models. arXiv."},{"key":"1036_CR3","unstructured":"Xie T, Zhao S, Wu CH, et al (2024) Text2Reward: Reward shaping with language models for reinforcement learning. In: The Twelfth International Conference on Learning Representations (ICLR 2024)"},{"key":"1036_CR4","unstructured":"Ma YJ, Liang W, Wang G, et al (2024) Eureka: Human-level reward design via coding large language models. In: The Twelfth International Conference on Learning Representations (ICLR 2024)."},{"key":"1036_CR5","doi-asserted-by":"publisher","first-page":"172","DOI":"10.3390\/make4010009","volume":"4","author":"M Hutsebaut-Buysse","year":"2022","unstructured":"Hutsebaut-Buysse M, Mets K, Latre S (2022) Hierarchical reinforcement learning: A survey and open research challenges. Mach Learn Knowledge Extract 4:172\u2013221","journal-title":"Mach Learn Knowledge Extract"},{"key":"1036_CR6","first-page":"154514","volume":"12","author":"S Takeda","year":"2025","unstructured":"Takeda S, Yamamori S, Yagi S et al (2025) An empirical evaluation of a hierarchical reinforcement learning method towards modular robot control. Artif Life Robotics 12:154514\u2013154525","journal-title":"Artif Life Robotics"},{"key":"1036_CR7","doi-asserted-by":"publisher","first-page":"4126","DOI":"10.1109\/LRA.2022.3146589","volume":"7","author":"Y Zhu","year":"2022","unstructured":"Zhu Y, Stone P, Zhu Y (2022) Bottom-up skill discovery from unsegmented demonstrations for long-horizon robot manipulation. IEEE Robotics and Autom Lett 7:4126\u20134133","journal-title":"IEEE Robotics and Autom Lett"},{"key":"1036_CR8","doi-asserted-by":"publisher","first-page":"4063","DOI":"10.1109\/LRA.2022.3150013","volume":"7","author":"J Zhu","year":"2022","unstructured":"Zhu J, Gienger M, Kober J (2022) Learning task-parameterized skills from few demonstrations. IEEE Robo Autom Lett 7:4063\u20134070","journal-title":"IEEE Robo Autom Lett"},{"key":"1036_CR9","doi-asserted-by":"crossref","unstructured":"Booth S, Knox WB, Shah J et al (2023) The perils of trial-and-error reward design: Misdesign through overfitting and invalid task specifications. In: Proceedings of the AAAI Conference on Intelligence, 37(5):5920\u20135929.","DOI":"10.1609\/aaai.v37i5.25733"},{"key":"1036_CR10","unstructured":"Yu W, Gileadi N, Fu C et al (2023) Language to rewards for robotic skill synthesis. In: Proceedings of The 7th Conference on Robot Learning, Proceedings of Machine Learning Research, 229:374\u2013404."},{"key":"1036_CR11","doi-asserted-by":"crossref","unstructured":"Li H, Yang X, Wang Z et al (2023) Auto mc-reward: Automated dense reward design with large language models for minecraft. In: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 16426\u201316435.","DOI":"10.1109\/CVPR52733.2024.01554"},{"key":"1036_CR12","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1016\/j.jmsy.2022.05.006","volume":"63","author":"R Zhang","year":"2022","unstructured":"Zhang R, Lv J, Li J et al (2022) A graph-based reinforcement learning-enabled approach for adaptive human-robot collaborative assembly operations. J Manuf Syst 63:491\u2013503","journal-title":"J Manuf Syst"},{"key":"1036_CR13","doi-asserted-by":"crossref","unstructured":"Schoettler G, Nair A, Ojea JA et al (2020) Meta-reinforcement learning for robotic industrial insertion tasks. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). pp. 9728\u20139735.","DOI":"10.1109\/IROS45743.2020.9340848"},{"key":"1036_CR14","first-page":"1","volume":"73","author":"J Gao","year":"2024","unstructured":"Gao J, Li Y, Chen Y et al (2024) An improved SAC-based deep reinforcement learning framework for collaborative pushing and grasping in underwater environments. IEEE Trans Instrum Meas 73:1\u201314","journal-title":"IEEE Trans Instrum Meas"},{"key":"1036_CR15","doi-asserted-by":"publisher","first-page":"6337","DOI":"10.1109\/LRA.2021.3092640","volume":"6","author":"H Xu","year":"2021","unstructured":"Xu H, Yu Q, Lai Y et al (2021) Efficient learning of goal-oriented push-grasping synergy in clutter. IEEE Robo Autom Lett 6:6337\u20136344","journal-title":"IEEE Robo Autom Lett"},{"key":"1036_CR16","doi-asserted-by":"publisher","first-page":"154514","DOI":"10.1109\/ACCESS.2024.3483970","volume":"12","author":"G Shin","year":"2024","unstructured":"Shin G, Yun S, Kim WT et al (2024) A novel policy distillation with WPA-based knowledge filtering algorithm for efficient industrial robot control. IEEE Access 12:154514\u2013154525","journal-title":"IEEE Access"},{"key":"1036_CR17","unstructured":"Tao S, Genc J, Chung T et al (2018) Repaint: Knowledge transfer in deep reinforcement learning. In: Meila M, Zhang T (eds) Proceedings of the 38th International Conference on Machine Learning (ICML\u201918). PMLR, pp 10141\u201310152."},{"key":"1036_CR18","unstructured":"Barreto A, Borsa D, Quan J et al (2018) Transfer in deep reinforcement learning using successor features and generalised policy improvement. In: Proceedings of the International Conference on Machine Learning."},{"key":"1036_CR19","unstructured":"Zhang A, Satija H, Pineau J (2018) Decoupling dynamics and reward for transfer learning. arXiv."},{"key":"1036_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2023.3305709","volume":"72","author":"Y Men","year":"2023","unstructured":"Men Y, Jin L, Cui T et al (2023) Policy fusion transfer: The knowledge transfer for different robot peg-in-hole insertion assemblies. IEEE Trans Instrum Meas 72:1\u201310","journal-title":"IEEE Trans Instrum Meas"},{"key":"1036_CR21","doi-asserted-by":"publisher","first-page":"2748","DOI":"10.1109\/TIE.2023.3269464","volume":"71","author":"L Jin","year":"2024","unstructured":"Jin L, Men Y, Song R et al (2024) Robot skill generalization: Feature-selected adaptation transfer for peg-in-hole assembly. IEEE Trans Industr Electron 71:2748\u20132757","journal-title":"IEEE Trans Industr Electron"},{"key":"1036_CR22","unstructured":"Touvron H, Lavril T, Izacard G et al (2023) Llama: Open and efficient foundation language models. arXiv ."},{"key":"1036_CR23","doi-asserted-by":"crossref","unstructured":"Reimers N, Gurevych I (2019) Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv.","DOI":"10.18653\/v1\/D19-1410"},{"key":"1036_CR24","doi-asserted-by":"publisher","first-page":"1699","DOI":"10.1109\/TCYB.2021.3108237","volume":"53","author":"H Shi","year":"2021","unstructured":"Shi H, Li J, Mao J et al (2021) Lateral transfer learning for multiagent reinforcement learning. IEEE Trans Cybern 53:1699\u20131711","journal-title":"IEEE Trans Cybern"},{"key":"1036_CR25","unstructured":"Mnih V, Badia AP, Mirza M et al (2016) Asynchronous methods for deep reinforcement learning. In: Proceedings of the 33rd International Conference on Machine Learning. JMLR.org, pp 1928\u20131937."},{"key":"1036_CR26","unstructured":"Makoviychuk V, Wawrzyniak L, Guo Y et al (2021) Isaac gym: High performance GPU based physics simulation for robot learning. In: Proceedings of the Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track."},{"key":"1036_CR27","doi-asserted-by":"crossref","unstructured":"Tessler C, Givony S, Zahavy T et al (2017) A deep hierarchical approach to lifelong learning in minecraft. In: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence. AAAI Press, pp 1553\u20131561.","DOI":"10.1609\/aaai.v31i1.10744"}],"container-title":["Artificial Life and Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10015-025-01036-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10015-025-01036-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10015-025-01036-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,16]],"date-time":"2025-11-16T20:48:07Z","timestamp":1763326087000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10015-025-01036-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,18]]},"references-count":27,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["1036"],"URL":"https:\/\/doi.org\/10.1007\/s10015-025-01036-y","relation":{},"ISSN":["1433-5298","1614-7456"],"issn-type":[{"value":"1433-5298","type":"print"},{"value":"1614-7456","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,18]]},"assertion":[{"value":"12 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 May 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 July 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}