{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T06:48:17Z","timestamp":1730270897931,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2008,9]]},"DOI":"10.1109\/iros.2008.4650873","type":"proceedings-article","created":{"date-parts":[[2008,10,15]],"date-time":"2008-10-15T12:31:19Z","timestamp":1224073879000},"page":"3635-3640","source":"Crossref","is-referenced-by-count":17,"title":["Policy gradient based Reinforcement Learning for real autonomous underwater cable tracking"],"prefix":"10.1109","author":[{"given":"A.","family":"El-Fakdi","sequence":"first","affiliation":[]},{"given":"M.","family":"Carreras","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"Neural Networks a Comprehensive Foundation 2nd Ed","year":"1999","author":"haykin","key":"19"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1007\/s001380100065"},{"journal-title":"Direct gradient-based reinforcement learning I Gradient estimation algorithms","year":"1999","author":"baxter","key":"17"},{"key":"23","article-title":"underwater cable tracking by visual feedback","author":"antich","year":"0","journal-title":"First Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA LNCS 2652) Port D'Andratx Spain 2003"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.282342"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1023\/A:1006559212014"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20171"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"journal-title":"Making reinforcement learning work on real robots","year":"2002","author":"smart","key":"14"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389841"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2005.1570759"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2004.01.004"},{"journal-title":"Approximating a Policy Can Be Easier Than Approximating a Value Function","year":"2000","author":"anderson","key":"3"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2007.363779"},{"key":"2","first-page":"1057","article-title":"policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"1"},{"key":"10","first-page":"2001","author":"meuleau","year":"2001","journal-title":"Exploration in Gradient Based Reinforcement Learning"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2004.1307456"},{"key":"6","article-title":"robot weightlifting by direct policy search","author":"rosenstein","year":"2001","journal-title":"Proceedings of the International Joint Conference on Artificial Intelligence"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2001.932842"},{"journal-title":"Policy-gradient algorithms for partially observable Markov decision processes","year":"2003","author":"aberdeen","key":"4"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012901385691"},{"journal-title":"Gradient-based Optimization of Markov Reward Processes Practical Variants","year":"2000","author":"marbach","key":"8"}],"event":{"name":"2008 IEEE\/RSJ International Conference on Intelligent Robots and Systems","start":{"date-parts":[[2008,9,22]]},"location":"Nice","end":{"date-parts":[[2008,9,26]]}},"container-title":["2008 IEEE\/RSJ International Conference on Intelligent Robots and Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/4637508\/4650570\/04650873.pdf?arnumber=4650873","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,16]],"date-time":"2017-03-16T16:11:42Z","timestamp":1489680702000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/4650873\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,9]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/iros.2008.4650873","relation":{},"subject":[],"published":{"date-parts":[[2008,9]]}}}