{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T08:36:25Z","timestamp":1771490185827,"version":"3.50.1"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"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":[[2022,10,23]]},"DOI":"10.1109\/iros47612.2022.9981182","type":"proceedings-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T14:38:15Z","timestamp":1672065495000},"page":"12566-12573","source":"Crossref","is-referenced-by-count":14,"title":["Deep Residual Reinforcement Learning based Autonomous Blimp Control"],"prefix":"10.1109","author":[{"given":"Yu Tang","family":"Liu","sequence":"first","affiliation":[{"name":"Max Planck Institute for Intelligent Systems.,Tübingen,Germany,72076"}]},{"given":"Eric","family":"Price","sequence":"additional","affiliation":[{"name":"Institute for Flight Mechanics and Controls,The Faculty of Aerospace Engineering and Geodesy,University of Stuttgart,Stuttgart,Germany,70569"}]},{"given":"Michael J.","family":"Black","sequence":"additional","affiliation":[{"name":"Max Planck Institute for Intelligent Systems.,Tübingen,Germany,72076"}]},{"given":"Aamir","family":"Ahmad","sequence":"additional","affiliation":[{"name":"Institute for Flight Mechanics and Controls,The Faculty of Aerospace Engineering and Geodesy,University of Stuttgart,Stuttgart,Germany,70569"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2000.894672"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1999.770044"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2007.908209"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ROMOCO.2005.201423"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2009.5420403"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-95892-3_46"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2002.1013654"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/s16010097"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CCA.2006.286205"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.asr.2018.09.008"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2007.363075"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-09997-9"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561138"},{"key":"ref23","first-page":"9","article-title":"Bridging theory and algorithm for domain adaptation","volume":"97","author":"zhang","year":"2019","journal-title":"Proceedings of the 36th International Conference on Machine Learning ser Proceedings of Machine Learning Research"},{"key":"ref26","first-page":"1491","article-title":"A flight control and navigation system of a small size unmanned airship","volume":"3","author":"rao","year":"0","journal-title":"IEEE International Conference Mechatronics and Automation"},{"key":"ref25","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152660"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/7854173"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2007.4399531"},{"key":"ref28","article-title":"What matters for on-policy deep actorcritic methods? a large-scale study","author":"andrychowicz","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CCA.2010.5611169"},{"key":"ref8","article-title":"Residual Policy Learning","author":"silver","year":"2018","journal-title":"ArXiv e-prints"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2939-8"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long Short-Term Memory","volume":"9","author":"hochreiter","year":"1997","journal-title":"Neural Computation"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2005.1570450"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10015-006-0385-9"},{"key":"ref6","first-page":"799","article-title":"Autonomous helicopter flight via reinforcement learning","author":"ng","year":"2003","journal-title":"Proceedings of the 16th International Conference on Neural Information Processing Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2019.105610"}],"event":{"name":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Kyoto, Japan","start":{"date-parts":[[2022,10,23]]},"end":{"date-parts":[[2022,10,27]]}},"container-title":["2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9981026\/9981028\/09981182.pdf?arnumber=9981182","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T18:01:21Z","timestamp":1701280881000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9981182\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,23]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/iros47612.2022.9981182","relation":{},"subject":[],"published":{"date-parts":[[2022,10,23]]}}}