{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T20:03:38Z","timestamp":1760385818630,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icra40945.2020.9196641","type":"proceedings-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T21:25:46Z","timestamp":1600205146000},"page":"1881-1887","source":"Crossref","is-referenced-by-count":3,"title":["DOB-Net: Actively Rejecting Unknown Excessive Time-Varying Disturbances"],"prefix":"10.1109","author":[{"given":"Tianming","family":"Wang","sequence":"first","affiliation":[]},{"given":"Wenjie","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Zheng","family":"Yan","sequence":"additional","affiliation":[]},{"given":"Dikai","family":"Liu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref10","article-title":"Active task design in adaptive control of redundant robotic systems","author":"lu","year":"2017","journal-title":"Australasian Conference on Robotics and Automation"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WCICA.2018.8630712"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/0959651815605664"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(89)90002-2"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.05.023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.329"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref17","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref18","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"article-title":"Meta reinforcement learning with latent variable gaussian processes","year":"2018","author":"s\u00e6mundsson","key":"ref19"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/9.895559"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1201\/b16570"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487660"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/41.857974"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2014.2305791"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2511450"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2015.2478397"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WCICA.2018.8630398"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1201\/9780203522301"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1201\/9781498701822"},{"key":"ref20","first-page":"271","article-title":"Reinforcement learning with hidden states","volume":"2","author":"lin","year":"1993","journal-title":"From Animals to Animats"},{"key":"ref22","article-title":"Deep recurrent q-learning for partially observable mdps","author":"hausknecht","year":"2015","journal-title":"2015 AAAI Fall Symposium Series"},{"key":"ref21","article-title":"Excessive disturbance rejection control of autonomous underwater vehicle using reinforcement learning","author":"wang","year":"2018","journal-title":"Australasian Conference on Robotics and Automation"},{"key":"ref24","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74690-4_71"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.2514\/6.2009-1983"}],"event":{"name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2020,5,31]]},"location":"Paris, France","end":{"date-parts":[[2020,8,31]]}},"container-title":["2020 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9187508\/9196508\/09196641.pdf?arnumber=9196641","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:17:52Z","timestamp":1656375472000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9196641\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icra40945.2020.9196641","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}