{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T03:12:34Z","timestamp":1775013154013,"version":"3.50.1"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["91748131"],"award-info":[{"award-number":["91748131"]}],"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":["62006229"],"award-info":[{"award-number":["62006229"]}],"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":["61771471"],"award-info":[{"award-number":["61771471"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"InnoHK Project"},{"name":"Strategic Priority Research Program of Chinese Academy of Science","award":["XDB32050100"],"award-info":[{"award-number":["XDB32050100"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tcds.2024.3406730","type":"journal-article","created":{"date-parts":[[2024,5,29]],"date-time":"2024-05-29T17:33:50Z","timestamp":1717004030000},"page":"2019-2031","source":"Crossref","is-referenced-by-count":4,"title":["Progressive Transfer Learning for Dexterous In-Hand Manipulation With Multifingered Anthropomorphic Hand"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0651-8794","authenticated-orcid":false,"given":"Yongkang","family":"Luo","sequence":"first","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7643-7132","authenticated-orcid":false,"given":"Wanyi","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8265-9866","authenticated-orcid":false,"given":"Peng","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3608-4467","authenticated-orcid":false,"given":"Haonan","family":"Duan","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9654-0981","authenticated-orcid":false,"given":"Wei","family":"Wei","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0560-9099","authenticated-orcid":false,"given":"Jia","family":"Sun","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2000.844067"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907864"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-41188-6"},{"key":"ref7","first-page":"1101","article-title":"Deep dynamics models for learning dexterous manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Nagabandi","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref9","article-title":"Distributed distributional deterministic policy gradients","author":"Barth-Maron","year":"2018"},{"issue":"3","key":"ref10","first-page":"207","article-title":"An overview of the developmental process for the modular prosthetic limb","volume":"30","author":"Johannes","year":"2011","journal-title":"Johns Hopkins APL Tech. Dig."},{"key":"ref11","article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","author":"Plappert","year":"2018"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1108\/01439910310457715"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.95.3.861"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1177\/02783649922066268"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICAR.2011.6088576"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487156"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574717000303"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2964160"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989331"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759394"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2016.2562122"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1115\/1.4052486"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abd9461"},{"issue":"30","key":"ref24","first-page":"1","article-title":"A review of robot learning for manipulation: Challenges, representations, and algorithms","volume":"22","author":"Kroemer","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3142417"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/icra46639.2022.9812212"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.3043675"},{"key":"ref28","first-page":"1496","article-title":"Solving challenging dexterous manipulation tasks with trajectory optimisation and reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Charlesworth","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920987859"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561384"},{"key":"ref31","first-page":"297","article-title":"A simple method for complex in-hand manipulation","volume-title":"Proc. 5th Annu. Conf. Robot Learn.","volume":"3","author":"Chen","year":"2021"},{"key":"ref32","article-title":"Generalization in dexterous manipulation via geometry-aware multi-task learning","author":"Huang","year":"2021"},{"key":"ref33","first-page":"297","article-title":"A system for general in-hand object re-orientation","volume-title":"Proc. Conf. Robot Learn.","author":"Chen","year":"2022"},{"issue":"7","key":"ref34","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"Taylor","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1017\/9781139061773"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3151646"},{"key":"ref37","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Haarnoja","year":"2017"},{"key":"ref38","article-title":"Stochastic neural networks for hierarchical reinforcement learning","author":"Florensa","year":"2017"},{"key":"ref39","article-title":"One solution is not all you need: Few-shot extrapolation via structured maxent RL","author":"Kumar","year":"2020"},{"key":"ref40","first-page":"688","article-title":"Adapting deep visuomotor representations with weak pairwise constraints","volume-title":"Proc. Workshop Algorithmic Found. Robot. (WAFR)","author":"Tzeng","year":"2016"},{"key":"ref41","article-title":"Off-dynamics reinforcement learning: Training for transfer with domain classifiers","author":"Eysenbach","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3028078"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2016.2607018"},{"key":"ref46","article-title":"Policy distillation","author":"Rusu","year":"2016"},{"key":"ref47","article-title":"Progressive reinforcement learning with distillation for multi-skilled motion control","author":"Berseth","year":"2018"},{"key":"ref48","first-page":"1787","article-title":"Contextual policy transfer in reinforcement learning domains via deep mixtures-of-experts","volume-title":"Proc. Uncertainty Artif. Intell. (UAI)","author":"Gimelfarb","year":"2021"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3107375"},{"key":"ref50","article-title":"Multi-source transfer learning for deep model-based reinforcement learning","author":"Sasso","year":"2022"},{"key":"ref51","article-title":"Progressive neural networks","author":"Rusu","year":"2016"},{"key":"ref52","first-page":"262","article-title":"Sim-to-real robot learning from pixels with progressive nets","volume-title":"Proc. Conf. Robot Learn.","author":"Rusu","year":"2017"},{"key":"ref53","first-page":"501","article-title":"Transfer in deep reinforcement learning using successor features and generalised policy improvement","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Barreto","year":"2018"},{"key":"ref54","article-title":"A new representation of successor features for transfer across dissimilar environments","author":"Abdolshah","year":"2021"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2017.2718938"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/iros47612.2022.9981458"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2021.3118294"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.3390\/technologies11020040"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3370034"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref61","article-title":"Prioritized experience replay","author":"Schaul","year":"2015"},{"issue":"9","key":"ref62","first-page":"1","article-title":"Experience selection in deep reinforcement learning for control","volume":"19","author":"Bruin","year":"2018","journal-title":"J. Mach. Learn. Res."},{"key":"ref63","first-page":"3061","article-title":"Revisiting fundamentals of experience replay","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fedus","year":"2020"},{"key":"ref64","article-title":"Don\u2019t change the algorithm, change the data: Exploratory data for offline reinforcement learning","author":"Yarats","year":"2022"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390225"},{"key":"ref66","first-page":"4936","article-title":"Importance weighted transfer of samples in reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tirinzoni","year":"2018"},{"key":"ref67","first-page":"6264","article-title":"Transfer of samples in policy search via multiple importance sampling","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tirinzoni","year":"2019"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10733"},{"key":"ref69","article-title":"MT-Opt: Continuous multi-task robotic reinforcement learning at scale","author":"Kalashniko","year":"2021"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2806087"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1038\/81497"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1523\/jneurosci.05-07-01688.1985"},{"key":"ref74","first-page":"1133","article-title":"Reconciling $\\lambda$-returns with experience replay","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Daley","year":"2019"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274989\/10774064\/10541306.pdf?arnumber=10541306","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T07:30:25Z","timestamp":1733297425000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10541306\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":74,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2024.3406730","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"value":"2379-8920","type":"print"},{"value":"2379-8939","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}