{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T14:37:08Z","timestamp":1784644628145,"version":"3.55.0"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Young Taishan Scholars Program","award":["tsqn202408072"],"award-info":[{"award-number":["tsqn202408072"]}]},{"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/lra.2026.3653285","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T23:58:44Z","timestamp":1768262324000},"page":"2642-2649","source":"Crossref","is-referenced-by-count":1,"title":["Transferring Policy of Offline Reinforcement Learning From Hybrid Dataset to Real World via Progressive Neural Network"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1764-5344","authenticated-orcid":false,"given":"Pengyu","family":"Zhao","sequence":"first","affiliation":[{"name":"College of Electronic Engineering, Ocean University of China, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9490-307X","authenticated-orcid":false,"given":"Zheng","family":"Fang","sequence":"additional","affiliation":[{"name":"College of Electronic Engineering, Ocean University of China, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1565-9463","authenticated-orcid":false,"given":"Tongxu","family":"Ai","sequence":"additional","affiliation":[{"name":"College of Electronic Engineering, Ocean University of China, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6826-4721","authenticated-orcid":false,"given":"Bo","family":"He","sequence":"additional","affiliation":[{"name":"College of Electronic Engineering, Ocean University of China, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1728-5711","authenticated-orcid":false,"given":"Guangliang","family":"Li","sequence":"additional","affiliation":[{"name":"College of Electronic Engineering, Ocean University of China, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00891-x"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i27.35095"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3250269"},{"key":"ref5","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020"},{"key":"ref6","article-title":"Importance of empirical sample complexity analysis for offline reinforcement learning","author":"Arnob","year":"2021"},{"key":"ref7","first-page":"470","article-title":"A dataset perspective on offline reinforcement learning","volume-title":"Proc. Conf. Lifelong Learn. Agents","author":"Schweighofer","year":"2022"},{"key":"ref8","article-title":"AWAC: Accelerating online reinforcement learning with offline datasets","author":"Nair","year":"2020"},{"key":"ref9","first-page":"425","article-title":"Finetuning offline world models in the real world","volume-title":"Proc. Conf. Robot Learn.","author":"Feng","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00573-6"},{"key":"ref11","article-title":"A survey of sim-to-real methods in RL: Progress, prospects and challenges with foundation models","author":"Da","year":"2025"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.65109\/ukyv4725"},{"key":"ref13","article-title":"Transfer from simulation to real world through learning deep inverse dynamics model","author":"Christiano","year":"2016"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref16","article-title":"Progressive neural networks","author":"Rusu","year":"2016"},{"key":"ref17","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":"ref18","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2019"},{"key":"ref19","first-page":"11761","article-title":"Stabilizing off-policy Q-learning via bootstrapping error reduction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar","year":"2019"},{"key":"ref20","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar","year":"2020"},{"key":"ref21","first-page":"62244","article-title":"Cal-QL: Calibrated offline RL pre-training for efficient online fine-tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Nakamoto","year":"2023"},{"key":"ref22","first-page":"1","article-title":"Offline reinforcement learning with implicit q-learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kostrikov","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i19.34206"},{"key":"ref24","first-page":"19165","article-title":"Q-value regularized transformer for offline reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hu","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3363530"},{"key":"ref26","article-title":"Hybrid RL: Using both offline and online data can make RL efficient","author":"Song","year":"2022"},{"key":"ref27","first-page":"36599","article-title":"When to trust your simulator: Dynamics-aware hybrid offline-and-online reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Niu","year":"2022"},{"key":"ref28","first-page":"27395","article-title":"Policy finetuning: Bridging sample-efficient offline and online reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xie","year":"2021"},{"key":"ref29","article-title":"MOORe: Model-based offline-to-online reinforcement learning","author":"Mao","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29633"},{"key":"ref31","article-title":"MOORL: A framework for integrating offline-online reinforcement learning","author":"Chaudhary","year":"2025"},{"key":"ref32","first-page":"42428","article-title":"Hybrid inverse reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ren","year":"2024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.16457"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26345"},{"issue":"11","key":"ref35","first-page":"2579","article-title":"Visualizing data using t-SNE.","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11359420\/11345976.pdf?arnumber=11345976","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T21:23:13Z","timestamp":1769203393000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11345976\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":35,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3653285","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}