{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T20:59:36Z","timestamp":1773521976383,"version":"3.50.1"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10610177","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"5448-5454","source":"Crossref","is-referenced-by-count":2,"title":["An offline learning of behavior correction policy for vision-based robotic manipulation"],"prefix":"10.1109","author":[{"given":"Qingxiuxiong","family":"Dong","sequence":"first","affiliation":[{"name":"Toshiba Corporation,Media AI Laboratory, Corporate Research and Development Center,Kawasaki,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Toshimitsu","family":"Kaneko","sequence":"additional","affiliation":[{"name":"Toshiba Corporation,Media AI Laboratory, Corporate Research and Development Center,Kawasaki,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masashi","family":"Sugiyama","sequence":"additional","affiliation":[{"name":"RIKEN,Center for Advanced Intelligence Project,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref2","article-title":"Rt-2: Visionlanguage-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023"},{"key":"ref3","article-title":"Qt-opt: Scalable deep reinforcement learning for vision-based robotic manipulation","volume-title":"Conference on Robot Learning","author":"Kalashnikov"},{"key":"ref4","article-title":"Mt-opt: Continuous multi-task robotic reinforcement learning at scale","author":"Kalashnikov","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968263"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-020-09907-y"},{"key":"ref7","first-page":"477","article-title":"Learning 6-dof grasping and pick-place using attention focus","volume-title":"Conference on Robot Learning","author":"Gualtieri"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.2974093"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3140817"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01337"},{"key":"ref11","article-title":"Residual policy learning","author":"Silver","year":"2018"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref13","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume":"33","author":"Kumar","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","volume-title":"International Conference on Learning Representations","author":"Yarats"},{"key":"ref15","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3250269"},{"key":"ref17","first-page":"28954","article-title":"Combo: Conservative offline model-based policy optimization","volume":"34","author":"Yu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume":"34","author":"Fujimoto","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","article-title":"Awac: Accelerating online reinforcement learning with offline datasets","author":"Nair","year":"2020"},{"key":"ref20","first-page":"7768","article-title":"Critic regularized regression","volume":"33","author":"Wang","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","article-title":"Should i run offline reinforcement learning or behavioral cloning?","volume-title":"International Conference on Learning Representations","author":"Kumar"},{"key":"ref22","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International Conference on Machine Learning","author":"Haarnoja"},{"key":"ref23","first-page":"417","article-title":"A workflow for offline model-free robotic reinforcement learning","volume-title":"Conference on Robot Learning","author":"Kumar"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0192-5"},{"key":"ref25","first-page":"11842","article-title":"Delving into deep imbalanced regression","volume-title":"International Conference on Machine Learning","author":"Yang"},{"key":"ref26","article-title":"Multi-view masked world models for visual robotic manipulation","volume-title":"International Conference on Machine Learning","author":"Seo"},{"key":"ref27","first-page":"1332","article-title":"Masked world models for visual control","volume-title":"Conference on Robot Learning","author":"Seo"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10610177.pdf?arnumber=10610177","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:45:23Z","timestamp":1723268723000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610177\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610177","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}