{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T15:08:01Z","timestamp":1773414481862,"version":"3.50.1"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11245919","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"18660-18667","source":"Crossref","is-referenced-by-count":1,"title":["Integrating Offline Pre-Training with Online Fine-Tuning: A Reinforcement Learning Approach for Robot Social Navigation"],"prefix":"10.1109","author":[{"given":"Run","family":"Su","sequence":"first","affiliation":[{"name":"Wuhan University of Science and Technology,School of Computer Science and Technology"}]},{"given":"Hao","family":"Fu","sequence":"additional","affiliation":[{"name":"Wuhan University of Science and Technology,School of Computer Science and Technology"}]},{"given":"Shuai","family":"Zhou","sequence":"additional","affiliation":[{"name":"Wuhan University of Science and Technology,School of Computer Science and Technology"}]},{"given":"Yingao","family":"Fu","sequence":"additional","affiliation":[{"name":"Wuhan University of Science and Technology,School of Computer Science and Technology"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794134"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2972868"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593871"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461113"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197379"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989037"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19457-3_1"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2008.4543489"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5654369"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202312"},{"key":"ref11","first-page":"1273","article-title":"Offline reinforcement learning as one big sequence modeling problem","volume":"34","author":"Janner","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref12","article-title":"Rvs: What is essential for offline rl via supervised learning?","author":"Emmons","year":"2021"},{"key":"ref13","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref14","article-title":"Accelerating online reinforcement learning with offline datasets","volume":"abs\/2006.09359","author":"Ashvin","year":"2020","journal-title":"CoRR"},{"key":"ref15","article-title":"Stabilizing off-policy q-learning via bootstrapping error reduction","volume":"32","author":"Kumar","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref16","article-title":"Offline reinforcement learning with implicit q-learning","author":"Kostrikov","year":"2021"},{"key":"ref17","first-page":"1702","article-title":"Offline-to-online reinforcement learning via balanced replay and pessimistic q-ensemble","volume-title":"Conference on Robot Learning","author":"Lee"},{"key":"ref18","first-page":"27 042","article-title":"Online decision transformer","volume-title":"international conference on machine learning","author":"Zheng"},{"issue":"2","key":"ref19","first-page":"229","article-title":"Reinforcement learning: An introduction","volume":"17","author":"Sutton","year":"1999","journal-title":"Robotica"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2314"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561595"},{"key":"ref22","article-title":"Large batch optimization for deep learning: Training bert in 76 minutes","author":"You","year":"2019"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Hangzhou, China","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11245919.pdf?arnumber=11245919","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:08:46Z","timestamp":1765519726000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11245919\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11245919","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}