{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,13]],"date-time":"2025-12-13T09:42:57Z","timestamp":1765618977651,"version":"3.48.0"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T00:00:00Z","timestamp":1756598400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T00:00:00Z","timestamp":1756598400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276028, U20A20167"],"award-info":[{"award-number":["62276028, U20A20167"]}],"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":["62276028, U20A20167"],"award-info":[{"award-number":["62276028, U20A20167"]}],"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":["62276028, U20A20167"],"award-info":[{"award-number":["62276028, U20A20167"]}],"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":["62276028, U20A20167"],"award-info":[{"award-number":["62276028, U20A20167"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003787","name":"Natural Science Foundation of Hebei Province","doi-asserted-by":"crossref","award":["F2021203079"],"award-info":[{"award-number":["F2021203079"]}],"id":[{"id":"10.13039\/501100003787","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003787","name":"Natural Science Foundation of Hebei Province","doi-asserted-by":"crossref","award":["F2021203079"],"award-info":[{"award-number":["F2021203079"]}],"id":[{"id":"10.13039\/501100003787","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003787","name":"Natural Science Foundation of Hebei Province","doi-asserted-by":"crossref","award":["F2021203079"],"award-info":[{"award-number":["F2021203079"]}],"id":[{"id":"10.13039\/501100003787","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003787","name":"Natural Science Foundation of Hebei Province","doi-asserted-by":"crossref","award":["F2021203079"],"award-info":[{"award-number":["F2021203079"]}],"id":[{"id":"10.13039\/501100003787","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Innovation Capability Improvement Plan Project of Hebei Province","award":["22567626H"],"award-info":[{"award-number":["22567626H"]}]},{"name":"Innovation Capability Improvement Plan Project of Hebei Province","award":["22567626H"],"award-info":[{"award-number":["22567626H"]}]},{"name":"Innovation Capability Improvement Plan Project of Hebei Province","award":["22567626H"],"award-info":[{"award-number":["22567626H"]}]},{"name":"Innovation Capability Improvement Plan Project of Hebei Province","award":["22567626H"],"award-info":[{"award-number":["22567626H"]}]},{"name":"CentralLeadingLocalScienceandTechnology DevelopmentFundProjectofHebeiProvince","award":["236Z1811G"],"award-info":[{"award-number":["236Z1811G"]}]},{"name":"CentralLeadingLocalScienceandTechnology DevelopmentFundProjectofHebeiProvince","award":["236Z1811G"],"award-info":[{"award-number":["236Z1811G"]}]},{"name":"CentralLeadingLocalScienceandTechnology DevelopmentFundProjectofHebeiProvince","award":["236Z1811G"],"award-info":[{"award-number":["236Z1811G"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s13042-025-02784-w","type":"journal-article","created":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T07:01:35Z","timestamp":1756623695000},"page":"10525-10539","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ARA-DRL: robot skill deep reinforcement learning based on analogical reasoning and self-attention"],"prefix":"10.1007","volume":"16","author":[{"given":"Yunchuan","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muqun","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenbai","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peiliang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,8,31]]},"reference":[{"key":"2784_CR1","unstructured":"Kalashnikov D et al (2021) Mt-opt: continuous multi-task robotic reinforcement learning at scale. arXiv preprint arXiv:2104.08212"},{"issue":"9","key":"2784_CR2","doi-asserted-by":"publisher","first-page":"14128","DOI":"10.1109\/TITS.2022.3144867","volume":"23","author":"L LeMero","year":"2022","unstructured":"LeMero L, Yi D, Dianati M, Mouzakitis A (2022) A survey on imitation learning techniques for end-to-end autonomous vehicles. IEEE Trans Intell Transp Syst 23(9):14128\u201314147","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"2784_CR3","unstructured":"Hong Z, Yang G, Agrawal P (2022) Bilinear value networks. In: Proceedings of the International Conference on Learning Representations, Virtual, Online, 1\u201315"},{"key":"2784_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2024.104904","volume":"186","author":"W Hu","year":"2025","unstructured":"Hu W, Huang B, Lee WW et al (2025) Dexterous in-hand manipulation of slender cylindrical objects through deep reinforcement learning with tactile sensing. Robot Auton Syst 186:104904","journal-title":"Robot Auton Syst"},{"issue":"3","key":"2784_CR5","doi-asserted-by":"publisher","first-page":"2759","DOI":"10.1109\/TIE.2022.3172754","volume":"70","author":"Z Bing","year":"2023","unstructured":"Bing Z et al (2023) Solving robotic manipulation with sparse reward reinforcement learning via graph-based diversity and proximity. IEEE Trans Industr Electron 70(3):2759\u20132769","journal-title":"IEEE Trans Industr Electron"},{"key":"2784_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126620","volume":"557","author":"Y Luo","year":"2023","unstructured":"Luo Y et al (2023) Relay hindsight experience replay: self-guided continual reinforcement learning for sequential object manipulation tasks with sparse rewards. Neurocomputing 557:126620","journal-title":"Neurocomputing"},{"issue":"3","key":"2784_CR7","doi-asserted-by":"publisher","first-page":"6590","DOI":"10.1109\/LRA.2022.3174258","volume":"7","author":"J Erskine","year":"2022","unstructured":"Erskine J, Lehnert C (2022) Developing cooperative policies for multi-stage reinforcement learning tasks. IEEE Robot Autom Lett 7(3):6590\u20136597","journal-title":"IEEE Robot Autom Lett"},{"key":"2784_CR8","doi-asserted-by":"crossref","unstructured":"Li B, Lu T, Li J, Lu N, Cai Y, Wang S (2020) Acder: augmented curiosity-driven experience replay. In: Proceedings of the 2020 IEEE International Conference on Robotics and Automation, 4218\u20134224","DOI":"10.1109\/ICRA40945.2020.9197421"},{"key":"2784_CR9","unstructured":"Chiappa AS, Vargas AM, Huang AZ, Mathis A (2023) Latent exploration for reinforcement learning. arXiv preprint arXiv:2305.20065 [cs.RO]. Advances in Neural Information Processing Systems (NeurIPS) 37 2023 (in press), Code available at this https URL"},{"key":"2784_CR10","doi-asserted-by":"crossref","unstructured":"Wang M, Jin Y, Montana G (2024) Goal-conditioned offline reinforcement learning through state space partitioning. Mach Learn 113(5):2435-2465","DOI":"10.1007\/s10994-023-06500-z"},{"key":"2784_CR11","unstructured":"Andrychowicz M, Wolski F, Ray A et al (2017) Hindsight experience replay. Advances in Neural Information Processing Systems 30: 5084-5058"},{"key":"2784_CR12","unstructured":"He Q, Zhuang L, Li H (2020) Soft hindsight experience replay. arXiv preprint arXiv:2002.02089"},{"key":"2784_CR13","unstructured":"Wu P, Zhang Y, Mao B et al (2024) Robot manipulation skills learning for sparse rewards. Control Theory & Applications\/Kongzhi Lilun Yu Yingyong 41(1)"},{"key":"2784_CR14","doi-asserted-by":"crossref","unstructured":"Zeng H, Zhang P, Li F et al (2023) Ahegc: adaptive hindsight experience replay with goal-amended curiosity module for robot control. IEEE Trans Neural Net Learn Syst 35(11):16602-16615","DOI":"10.1109\/TNNLS.2023.3296765"},{"key":"2784_CR15","doi-asserted-by":"crossref","unstructured":"Vahabpour A, Wang T, Lu Q et al (2024) Diverse imitation learning via self-organizing generative models. IEEE Trans Neural Net Learn Syst 36(4):7145-7157","DOI":"10.1109\/TNNLS.2024.3401170"},{"issue":"2","key":"2784_CR16","first-page":"2097","volume":"27","author":"J Sun","year":"2024","unstructured":"Sun J, Li W (2024) Efficient hindsight experience replay with transformed data augmentation. J Appl Sci Eng 27(2):2097\u20132108","journal-title":"J Appl Sci Eng"},{"key":"2784_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121467","volume":"237","author":"Z Huang","year":"2024","unstructured":"Huang Z, Liu Q, Zhu F et al (2024) Hierarchical reinforcement learning with unlimited option scheduling for sparse rewards in continuous spaces. Expert Syst Appl 237:121467","journal-title":"Expert Syst Appl"},{"key":"2784_CR18","unstructured":"Rana K, Xu M, Tidd B, Milford M, Suenderhauf N (2023) Residual skill policies: learning an adaptable skill-based action space for reinforcement learning for robotics. In: Proceedings of the 6th Conference on Robot Learning. PMLR, 205:2095\u20132104"},{"key":"2784_CR19","unstructured":"Wang Z, Jiang M (2023) Enhancing data efficiency in reinforcement learning: a novel imagination mechanism based on mesh information propagation. arXiv preprint arXiv:2309.14243"},{"key":"2784_CR20","doi-asserted-by":"crossref","unstructured":"Reizinger P, Szemenyei M (2020) Attention-based curiosity-driven exploration in deep reinforcement learning. Proceedings of IEEE international conference on acoustics, speech and signal processing, 3542\u20133546","DOI":"10.1109\/ICASSP40776.2020.9054546"},{"key":"2784_CR21","unstructured":"Campero A, Raileanu R, Kuttler H, Tenenbaum JB, Rocktaschel T, Grefenstette E (2021) Learning with amigo: Adversarially motivated intrinsic goals. ICLR"},{"key":"2784_CR22","unstructured":"Ghosh D, Gupta A, Reddy A, Fu J, Devin C, Eysenbach B, Levine S (2021) Learning to reach goals via iterated supervised learning. ICLR"},{"issue":"1","key":"2784_CR23","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1007\/s12065-022-00703-4","volume":"17","author":"C Lu","year":"2024","unstructured":"Lu C, Bao Q, Xia S et al (2024) Centralized reinforcement learning for multi-agent cooperative environments. Evol Intel 17(1):267\u2013273","journal-title":"Evol Intel"},{"key":"2784_CR24","unstructured":"Hu K, Zheng RC, Gao Y et al (2023) Decision transformer under random frame dropping. arXiv preprint arXiv:2303.03391"},{"key":"2784_CR25","first-page":"15084","volume":"34","author":"L Chen","year":"2021","unstructured":"Chen L, Lu K, Rajeswaran A et al (2021) Decision transformer: reinforcement learning via sequence modeling. Adv Neural Inf Process Syst 34:15084\u201315097","journal-title":"Adv Neural Inf Process Syst"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02784-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-025-02784-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02784-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,13]],"date-time":"2025-12-13T09:40:30Z","timestamp":1765618830000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-025-02784-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,31]]},"references-count":25,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["2784"],"URL":"https:\/\/doi.org\/10.1007\/s13042-025-02784-w","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"type":"print","value":"1868-8071"},{"type":"electronic","value":"1868-808X"}],"subject":[],"published":{"date-parts":[[2025,8,31]]},"assertion":[{"value":"14 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 August 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}