{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T18:23:45Z","timestamp":1777487025147,"version":"3.51.4"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"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":["51809246"],"award-info":[{"award-number":["51809246"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014761","name":"Natural Science Foundation of Qingdao Municipality","doi-asserted-by":"publisher","award":["23-2-1-153-zyyd-jch"],"award-info":[{"award-number":["23-2-1-153-zyyd-jch"]}],"id":[{"id":"10.13039\/501100014761","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Honda Research Institute Japan Company, Ltd"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1109\/lra.2024.3370034","type":"journal-article","created":{"date-parts":[[2024,2,27]],"date-time":"2024-02-27T19:28:38Z","timestamp":1709062118000},"page":"3696-3703","source":"Crossref","is-referenced-by-count":5,"title":["Transferring Meta-Policy From Simulation to Reality via Progressive Neural Network"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-0176-8704","authenticated-orcid":false,"given":"Wei","family":"Meng","sequence":"first","affiliation":[{"name":"School of Information Science and Engineering, Ocean University of China, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5341-8263","authenticated-orcid":false,"given":"Hao","family":"Ju","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Ocean University of China, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1565-9463","authenticated-orcid":false,"given":"Tongxu","family":"Ai","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Ocean University of China, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3191-6818","authenticated-orcid":false,"given":"Randy","family":"Gomez","sequence":"additional","affiliation":[{"name":"Honda Research Institute Japan Company, Ltd., Wako, Saitama, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0734-6621","authenticated-orcid":false,"given":"Eric","family":"Nichols","sequence":"additional","affiliation":[{"name":"Honda Research Institute Japan Company, Ltd., Wako, Saitama, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1728-5711","authenticated-orcid":false,"given":"Guangliang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Ocean University of China, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref2","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v31i3.2303"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref6","article-title":"Deep reinforcement learning for autonomous driving","author":"Wang","year":"2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00573-6"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref12","first-page":"1859","article-title":"Domain adaptation for reinforcement learning on the atari","volume-title":"Proc. 18th Int. Conf. Auton. Agents MultiAgent Syst.","author":"Carr","year":"2019"},{"key":"ref13","article-title":"Transfer from simulation to real world through learning deep inverse dynamics model","author":"Christiano","year":"2016"},{"key":"ref14","article-title":"Progressive neural networks","author":"Rusu","year":"2016"},{"key":"ref15","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn","year":"2017"},{"key":"ref16","first-page":"262","article-title":"Sim-to-real robot learning from pixels with progressive nets","volume-title":"Proc. 1st Annu. Conf. Robot Learn.","author":"Rusu","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/s41593-018-0147-8"},{"key":"ref18","article-title":"Towards adapting deep visuomotor representations from simulated to real environments","author":"Tzeng","year":"2015"},{"key":"ref19","article-title":"Learning invariant feature spaces to transfer skills with reinforcement learning","volume-title":"Proc. Int.Conf. Learn. Representations","author":"Gupta","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05982-z"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161298"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636061"},{"key":"ref24","article-title":"On first-order meta-learning algorithms","author":"Nichol","year":"2018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196540"},{"key":"ref26","first-page":"1","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Nagabandi","year":"2019"},{"key":"ref27","first-page":"617","article-title":"Model-based reinforcement learning via meta-policy optimization","volume-title":"Proc. 2nd Conf. Robot Learn.","author":"Clavera","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref29","article-title":"Evolutionary principles in self-referential learning","volume-title":"Genet. Program.","author":"Schmidhuber","year":"1987"},{"key":"ref30","article-title":"A survey of meta-reinforcement learning","author":"Beck","year":"2023"},{"key":"ref31","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref32","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman","year":"2015"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/10440130\/10449466.pdf?arnumber=10449466","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T17:33:10Z","timestamp":1745947990000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10449466\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4]]},"references-count":33,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/lra.2024.3370034","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4]]}}}