{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:37:10Z","timestamp":1774539430631,"version":"3.50.1"},"reference-count":20,"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\/iros47612.2022.9981425","type":"proceedings-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:38:15Z","timestamp":1672083495000},"page":"7036-7043","source":"Crossref","is-referenced-by-count":11,"title":["Autonomous Control of Redundant Hydraulic Manipulator Using Reinforcement Learning with Action Feedback"],"prefix":"10.1109","author":[{"given":"Rohit","family":"Dhakate","sequence":"first","affiliation":[{"name":"University of Klagenfurt,Department of Smart Systems Technologies in the Control of Networked Systems Group,Klagenfurt,Austria,9020"}]},{"given":"Christian","family":"Brommer","sequence":"additional","affiliation":[{"name":"University of Klagenfurt,Department of Smart Systems Technologies in the Control of Networked Systems Group,Klagenfurt,Austria,9020"}]},{"given":"Christoph","family":"Bohm","sequence":"additional","affiliation":[{"name":"University of Klagenfurt,Department of Smart Systems Technologies in the Control of Networked Systems Group,Klagenfurt,Austria,9020"}]},{"given":"Harald","family":"Gietler","sequence":"additional","affiliation":[{"name":"University of Klagenfurt,Department of Smart Systems Technologies in the Sensors and Actuators Group,Klagenfurt,Austria,9020"}]},{"given":"Stephan","family":"Weiss","sequence":"additional","affiliation":[{"name":"University of Klagenfurt,Department of Smart Systems Technologies in the Control of Networked Systems Group,Klagenfurt,Austria,9020"}]},{"given":"Jan","family":"Steinbrener","sequence":"additional","affiliation":[{"name":"University of Klagenfurt,Department of Smart Systems Technologies in the Control of Networked Systems Group,Klagenfurt,Austria,9020"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5552\/crojfe.2019.501"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3182\/20080706-5-KR-1001.00389"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1155\/2015\/256951"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAS.2015.7364729"},{"issue":"7540","key":"ref5","first-page":"529","article-title":"Human-level control through deep reinforcement learning","volume-title":"Nature","volume":"518","author":"Mnih","year":"2015"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"ref7","first-page":"1928","article-title":"Asynchronous methods for deep rein- forcement learning","volume-title":"International conference on machine learning","author":"Mnih"},{"key":"ref8","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"ar Xiv preprint"},{"key":"ref9","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proceedings of the 32nd International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","volume":"37","author":"Schulman","year":"2015"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341598"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636219"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/I2MTC43012.2020.9129237"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696520"},{"key":"ref14","volume-title":"Bullet real-time physics simulation","author":"Coumans","year":"2013"},{"key":"ref15","author":"Smith","year":"2007","journal-title":"Open dynamics engine"},{"key":"ref16","article-title":"Vortex studio","year":"2020","journal-title":"CM Labs"},{"key":"ref17","article-title":"Newton game dynamics","author":"Jerez","year":"2008","journal-title":"Opensource Physics Engine"},{"key":"ref18","article-title":"Continuous control with deep reinforce-ment learning","author":"Lillicrap","year":"2015","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Deep reinforcement learning that matters","volume-title":"CoRR, vol. abs\/1709.06560","author":"Henderson","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"}],"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\/09981425.pdf?arnumber=9981425","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T03:49:42Z","timestamp":1710388182000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9981425\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,23]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/iros47612.2022.9981425","relation":{},"subject":[],"published":{"date-parts":[[2022,10,23]]}}}