{"id":107155,"date":"2011-03-03T00:00:00","date_gmt":"2011-03-03T00:00:00","guid":{"rendered":"https:\/\/www.deberes.net\/tesis\/sin-categoria\/gradient-based-reinforcement-learning-techniques-for-underwater-robotics-behavior-learning\/"},"modified":"2011-03-03T00:00:00","modified_gmt":"2011-03-03T00:00:00","slug":"gradient-based-reinforcement-learning-techniques-for-underwater-robotics-behavior-learning","status":"publish","type":"post","link":"https:\/\/www.deberes.net\/tesis\/inteligencia-artificial\/gradient-based-reinforcement-learning-techniques-for-underwater-robotics-behavior-learning\/","title":{"rendered":"Gradient-based reinforcement learning techniques for underwater robotics behavior learning"},"content":{"rendered":"<h2>Tesis doctoral de <strong> Andres El-fakdi Sencianes <\/strong><\/h2>\n<p>\u00faltimamente, el inter\u00e9s por el desarrollo de aplicaciones con robots submarinos aut\u00f3nomos (auv) ha crecido de forma considerable. Los auvs son atractivos por su tama\u00f1o y porque no necesitan un operador humano para su pilotaje. A\u00fan y as\u00ed, es imposible comparar, en t\u00e9rminos de eficiencia y flexibilidad, la habilidad del pilotaje humano con las escasas capacidades operativas que ofrecen los auvs actuales. El uso de auvs para cubrir grandes \u00e1reas implica resolver problemas complejos, especialmente si se desea que el robot reaccione en tiempo real a cambios bruscos que pudieran producirse en las condiciones de trabajo. Por estas razones, el desarrollo de sistemas de control aut\u00f3nomo para mejorar estas capacidades se ha convertido en una prioridad.   esta tesis trata sobre el problema de la toma de decisiones utilizando auvs. El trabajo presentado se centra en el estudio, dise\u00f1o y aplicaci\u00f3n de comportamientos para auvs utilizando t\u00e9cnicas de aprendizaje por refuerzo (rl). La contribuci\u00f3n principal de la tesis consiste en la aplicaci\u00f3n de varias t\u00e9cnicas que permiten mejorar la autonom\u00eda de los robots submarinos, con el objetivo final de demostrar la viabilidad de estos algoritmos para aprender tareas submarinas de forma aut\u00f3noma en tiempo real. En rl, el robot intenta maximizar un refuerzo escalar obtenido como consecuencia de su interacci\u00f3n con el entorno. El objetivo es encontrar una pol\u00edtica \u00f3ptima que relaciona todos los estados posibles con las acciones a ejecutar para cada estado que maximizan la suma de refuerzos totales. As\u00ed, esta tesis investiga principalmente dos tipolog\u00edas de algoritmos basados en rl: m\u00e9todos basados en funciones de valor (vf) y m\u00e9todos basados en el gradiente (pg). Los resultados experimentales finales muestran al robot submarino ictineu en una tarea aut\u00f3noma real de seguimiento de cables submarinos. Para llevarla a cabo, se ha dise\u00f1ado un algoritmo llamado m\u00e9todo del actor y el cr\u00edtico (ac), fruto de la fusi\u00f3n de m\u00e9todos vf con t\u00e9cnicas de pg.<\/p>\n<p>&nbsp;<\/p>\n<h3>Datos acad\u00e9micos de la tesis doctoral \u00ab<strong>Gradient-based reinforcement learning techniques for underwater robotics behavior learning<\/strong>\u00ab<\/h3>\n<ul>\n<li><strong>T\u00edtulo de la tesis:<\/strong>\u00a0 Gradient-based reinforcement learning techniques for underwater robotics behavior learning <\/li>\n<li><strong>Autor:<\/strong>\u00a0 Andres El-fakdi Sencianes <\/li>\n<li><strong>Universidad:<\/strong>\u00a0 Girona<\/li>\n<li><strong>Fecha de lectura de la tesis:<\/strong>\u00a0 03\/03\/2011<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<h3>Direcci\u00f3n y tribunal<\/h3>\n<ul>\n<li><strong>Director de la tesis<\/strong>\n<ul>\n<li>Marc Carreras P\u00e9rez<\/li>\n<\/ul>\n<\/li>\n<li><strong>Tribunal<\/strong>\n<ul>\n<li>Presidente del tribunal: pere Ridao rodriguez <\/li>\n<li>petar Stefanov kormushev (vocal)<\/li>\n<li>massimo Caccia (vocal)<\/li>\n<li>cecilio Angulo bahon (vocal)<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Tesis doctoral de Andres El-fakdi Sencianes \u00faltimamente, el inter\u00e9s por el desarrollo de aplicaciones con robots submarinos aut\u00f3nomos (auv) ha [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"default","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""}},"footnotes":""},"categories":[18809,2528,7742],"tags":[215346,79284,74128,215348,38014,215347],"class_list":["post-107155","post","type-post","status-publish","format-standard","hentry","category-girona","category-inteligencia-artificial","category-robotica","tag-andres-el-fakdi-sencianes","tag-cecilio-angulo-bahon","tag-marc-carreras-perez","tag-massimo-caccia","tag-pere-ridao-rodriguez","tag-petar-stefanov-kormushev"],"_links":{"self":[{"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/posts\/107155","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/comments?post=107155"}],"version-history":[{"count":0,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/posts\/107155\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/media?parent=107155"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/categories?post=107155"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/tags?post=107155"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}