{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T11:01:48Z","timestamp":1758279708563,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1109\/adprl.2014.7010621","type":"proceedings-article","created":{"date-parts":[[2015,1,20]],"date-time":"2015-01-20T02:48:03Z","timestamp":1421722083000},"page":"1-8","source":"Crossref","is-referenced-by-count":13,"title":["Multi-objective reinforcement learning for AUV thruster failure recovery"],"prefix":"10.1109","author":[{"given":"Seyed Reza","family":"Ahmadzadeh","sequence":"first","affiliation":[]},{"given":"Petar","family":"Kormushev","sequence":"additional","affiliation":[]},{"given":"Darwin G.","family":"Caldwell","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v25i1.7903","article-title":"Value function approximation in reinforcement learning using the fourier basis","author":"konidaris","year":"2011","journal-title":"AAAI"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/OCEANSSYD.2010.5603565"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913499192"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/OCEANS.1998.724352"},{"key":"ref13","article-title":"Fin failure compensation for an unmanned underwater vehicle","author":"cheng","year":"1999","journal-title":"Proceedings of the 6th International Symposium on Unmanned Untethered Submersible Technology,"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1504\/IJIDSS.2011.037805"},{"key":"ref15","first-page":"197","article-title":"Multi-criteria reinforcement learning","volume":"98","author":"g\u00e1bor","year":"1998","journal-title":"ICML"},{"key":"ref16","first-page":"325","article-title":"A geometric approach to multi-criterion reinforcement learning","volume":"5","author":"mannor","year":"2004","journal-title":"The Journal of Machine Learning Research"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102427"},{"key":"ref18","first-page":"695","article-title":"Efficient reinforcement learning with multiple reward functions for randomized controlled trial analysis","author":"lizotte","year":"2010","journal-title":"Proceedings of the 27th International Conference on Machine Learning (ICML-10)"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"372","DOI":"10.1007\/978-3-540-89378-3_37","article-title":"On the limitations of scalarisation for multi-objective reinforcement learning of Pareto fronts","author":"vamplew","year":"2008","journal-title":"AI 2008 Advances in Artificial Intelligence"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2011.2174065"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907821"},{"key":"ref27","article-title":"Multi-objective differential evolution (mode): an evolutionary algorithm for multi-objective optimization problems (moops)","author":"babu","year":"2005","journal-title":"Proceedings of International Symposium and 58th Annual Session of IIChE"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45737-2_4"},{"key":"ref6","article-title":"On-line learning to recover from thruster failures on autonomous underwater vehicles","author":"leonetti","year":"2013","journal-title":"Oceans 2013"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696908"},{"key":"ref5","article-title":"Online direct policy search for thruster failure recovery in autonomous underwater vehicles","author":"ahmadzadeh","year":"2013","journal-title":"6th International Workshop on Evolutionary and Reinforcement Learning for Autonomous Robot System (ERLARS 2013)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/S0921-8890(00)00100-7"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2000.844770"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2001.933116"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2010.5718157"},{"key":"ref1","article-title":"Experiences on actuator fault detection, diagnosis and accomodation for ROVs","author":"caccia","year":"2001","journal-title":"International Symposiyum of Unmanned Untethered Sub-mersible Technol"},{"article-title":"Importance sampling for reinforcement learning with multiple objectives","year":"2001","author":"shelton","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2011.03.001"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390162"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2003.1299429"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008202821328"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2001.934295"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/11844297_59"}],"event":{"name":"2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","start":{"date-parts":[[2014,12,9]]},"location":"Orlando, FL, USA","end":{"date-parts":[[2014,12,12]]}},"container-title":["2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7000183\/7010603\/07010621.pdf?arnumber=7010621","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T04:31:27Z","timestamp":1690864287000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7010621\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,12]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/adprl.2014.7010621","relation":{},"subject":[],"published":{"date-parts":[[2014,12]]}}}