{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T12:18:31Z","timestamp":1783340311162,"version":"3.54.6"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icra.2019.8794127","type":"proceedings-article","created":{"date-parts":[[2019,8,12]],"date-time":"2019-08-12T21:26:12Z","timestamp":1565645172000},"page":"6023-6029","source":"Crossref","is-referenced-by-count":322,"title":["Residual Reinforcement Learning for Robot Control"],"prefix":"10.1109","author":[{"given":"Tobias","family":"Johannink","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shikhar","family":"Bahl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ashvin","family":"Nair","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianlan","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Avinash","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthias","family":"Loskyll","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan Aparicio","family":"Ojea","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eugen","family":"Solowjow","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sergey","family":"Levine","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref32","author":"silver","year":"2018","journal-title":"Residual Policy Learning"},{"key":"ref31","article-title":"Pseudo-Control Hedging: A New Method For Adaptive Control","author":"johnson","year":"2000","journal-title":"Advances in Navigation Guidance and Control Technology Workshop"},{"key":"ref30","article-title":"Structured Control Nets for Deep Reinforcement Learning","author":"srouji","year":"2018","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref11","first-page":"1334","article-title":"End-to-End Training of Deep Visuomotor Policies","volume":"17","author":"levine","year":"2016","journal-title":"Journal of Machine Learning Research (JMLR)"},{"key":"ref12","article-title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","author":"haarnoja","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref13","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","author":"ng","year":"1999","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref14","article-title":"Data-efficient Deep Reinforcement Learning for Dexterous Manipulation","volume":"abs 1704 0","author":"popov","year":"2017","journal-title":"CoRR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2014.X.031"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460696"},{"key":"ref17","first-page":"937","article-title":"A Strategy-Aware Technique for Learning Behaviors from Discrete Human Feedback","author":"loftin","year":"2014","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"ref18","article-title":"Trial without Error: Towards Safe Reinforcement Learning via Human Intervention","author":"saunders","year":"2018","journal-title":"International Conference on Autonomous Agents and Multiagent Systems (AAMAS)"},{"key":"ref19","article-title":"Teaching on a Budget: Agents Advising Agents in Reinforcement Learning","author":"torrey","year":"2013","journal-title":"International Conference on Autonomous Agents and Multiagent Systems (AAMAS)"},{"key":"ref28","article-title":"Exploration from Demonstration for Interactive Reinforcement Learning","author":"subramanian","year":"2016","journal-title":"International Conference on Autonomous Agents and Multiagent Systems (AAMAS)"},{"key":"ref4","article-title":"Temporal Difference Models: Model-Free Deep RL For Model-Based Control","author":"pong","year":"2018","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref3","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref6","first-page":"1607","article-title":"Relative Entropy Policy Search","author":"peters","year":"2010","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref8","article-title":"Robust Adversarial Reinforcement Learning","author":"pinto","year":"2017","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref7","first-page":"465","article-title":"PILCO: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref2","article-title":"Addressing Function Approximation Error in Actor-Critic Methods","author":"fujimoto","year":"2018","journal-title":"arXiv preprint arxiv 1802 05807"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48466-2_4"},{"key":"ref9","article-title":"Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection","author":"levine","year":"2017","journal-title":"International Journal of Robotics Research"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390199"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2008.02.003"},{"key":"ref21","article-title":"Deep reinforcement learning from human pReferences","author":"christiano","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"ref23","first-page":"83","article-title":"Policy search for motor primitives in robotics","volume":"97","author":"kober","year":"2008","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref26","article-title":"Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards","volume":"abs 1707 0","author":"ve?er\u00edk","year":"2017","journal-title":"CoRR"},{"key":"ref25","article-title":"Learning from Demonstrations for Real World Reinforcement Learning","author":"hester","year":"2018","journal-title":"AAAI Conference on Artificial Intelligence"}],"event":{"name":"2019 International Conference on Robotics and Automation (ICRA)","location":"Montreal, QC, Canada","start":{"date-parts":[[2019,5,20]]},"end":{"date-parts":[[2019,5,24]]}},"container-title":["2019 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8780387\/8793254\/08794127.pdf?arnumber=8794127","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,14]],"date-time":"2022-07-14T23:09:06Z","timestamp":1657840146000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8794127\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icra.2019.8794127","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}