{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T22:34:05Z","timestamp":1767998045633,"version":"3.49.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"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":[[2021,9,27]]},"DOI":"10.1109\/iros51168.2021.9636176","type":"proceedings-article","created":{"date-parts":[[2021,12,16]],"date-time":"2021-12-16T15:45:38Z","timestamp":1639669538000},"page":"2383-2390","source":"Crossref","is-referenced-by-count":9,"title":["Residual Feedback Learning for Contact-Rich Manipulation Tasks with Uncertainty"],"prefix":"10.1109","author":[{"given":"Alireza","family":"Ranjbar","sequence":"first","affiliation":[]},{"given":"Ngo Anh","family":"Vien","sequence":"additional","affiliation":[]},{"given":"Hanna","family":"Ziesche","sequence":"additional","affiliation":[]},{"given":"Joschka","family":"Boedecker","sequence":"additional","affiliation":[]},{"given":"Gerhard","family":"Neumann","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2004.840053"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2017.2671342"},{"key":"ref12","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6095096"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793485"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7138994"},{"key":"ref16","article-title":"One-shot learning of manipulation skills with online dynamics adaptation and neural network priors","author":"fu","year":"2015","journal-title":"CoRR"},{"key":"ref17","article-title":"Metareinforcement learning for robotic industrial insertion tasks","author":"schoettler","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341390"},{"key":"ref19","article-title":"Stable reinforcement learning with autoencoders for tactile and visual data","author":"hoof","year":"2016"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202244"},{"key":"ref4","article-title":"Residual policy learning","author":"silver","year":"2018"},{"key":"ref27","article-title":"Scalable trust-region method for deep reinforcement learning using kronecker-factored approximation","author":"wu","year":"2017"},{"key":"ref3","article-title":"Adaptive curriculum generation from demonstrations for sim-to-real visuomotor control","author":"hermann","year":"2019"},{"key":"ref6","article-title":"Residual reactive navigation: Combining classical and learned navigation strategies for deployment in unknown environments","author":"rana","year":"2019"},{"key":"ref5","article-title":"Deep reinforcement learning for industrial insertion tasks with visual inputs and natural rewards","author":"schoettler","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1243\/PIME_PROC_1993_207_134_02"},{"key":"ref7","article-title":"Multipolar: Multi-source policy aggregation for transfer reinforcement learning between diverse environmental dynamics","author":"barekatain","year":"2019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793542"},{"key":"ref9","article-title":"Transferable force-torque dynamics model for peg-in-hole task","author":"ding","year":"2019"},{"key":"ref1","article-title":"Residual reinforcement learning for robot control","author":"johannink","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202244"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1108\/01439910710774386"},{"key":"ref21","article-title":"Fast robust peg-in-hole insertion with continuous visual servoing","author":"haugaard","year":"2020","journal-title":"arXiv preprint arXiv 2011 00177"},{"key":"ref24","article-title":"Pytorch implementations of reinforcement learning algorithms","author":"kostrikov","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2011.2158251"},{"key":"ref26","article-title":"Blender - a 3d modelling and rendering package","year":"0","journal-title":"Blender Foundation"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"}],"event":{"name":"2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Prague, Czech Republic","start":{"date-parts":[[2021,9,27]]},"end":{"date-parts":[[2021,10,1]]}},"container-title":["2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9635848\/9635849\/09636176.pdf?arnumber=9636176","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T12:54:54Z","timestamp":1652187294000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9636176\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,27]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/iros51168.2021.9636176","relation":{},"subject":[],"published":{"date-parts":[[2021,9,27]]}}}