{"id":6626,"date":"2021-12-02T12:15:04","date_gmt":"2021-12-02T12:15:04","guid":{"rendered":"https:\/\/www.digitalfutures.kth.se\/?page_id=6626"},"modified":"2022-08-09T09:59:38","modified_gmt":"2022-08-09T07:59:38","slug":"alexandre-proutiere","status":"publish","type":"page","link":"https:\/\/wpmu-tris.sys.kth.se\/digitalfutures\/research\/digital-futures-fellows\/alexandre-proutiere\/","title":{"rendered":"Alexandre Proutiere"},"content":{"rendered":"<p><i>Title of the project<br \/>\n<\/i><strong>Data-efficient Reinforcement Learning<\/strong><\/p>\n<p><em><span class=\"TextRun MacChromeBold SCXW159808564 BCX0\" lang=\"EN-US\" xml:lang=\"EN-US\" data-contrast=\"auto\"><span class=\"NormalTextRun SCXW159808564 BCX0\">Background<\/span><span class=\"NormalTextRun SCXW159808564 BCX0\">\u00a0<\/span><span class=\"NormalTextRun SCXW159808564 BCX0\">and summary of fellowship<\/span><span class=\"NormalTextRun SCXW159808564 BCX0\">:<br \/>\n<\/span><\/span><\/em>Reinforcement Learning (RL) is concerned with learning efficient control policies for systems with unknown dynamics and reward functions. RL plays an increasingly important\u00a0role in a large spectrum of application domains including online platforms (recommender systems and search engines), robotics, and self-driving vehicles. Over the last decade, RL algorithms, combined with modern function approximators such as deep neural networks, have shown unprecedented performance and have been able to solve very complex sequential decision tasks better than humans. Yet, these algorithms are lacking robustness, and are most often extremely data inefficient.<\/p>\n<p>This research project aims at contributing to the theoretical foundations for the design of data-efficient and robust RL algorithms. To this aim, we develop a fundamental two-step process:<\/p>\n<ol>\n<li>We characterize information-theoretical limits for the performance of RL algorithms (in terms of sample complexity, i.e., data efficiency)<\/li>\n<li>We leverage these limits to guide the design of optimal RL algorithms, algorithms approaching the fundamental performance limits<\/li>\n<\/ol>\n","protected":false},"excerpt":{"rendered":"<p>Data-efficient Reinforcement Learning<\/p>\n","protected":false},"author":46,"featured_media":0,"parent":6563,"menu_order":255,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-6626","page","type-page","status-publish","hentry"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.8 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Alexandre Proutiere &#8212; Digital Futures<\/title>\n<meta name=\"robots\" content=\"noindex, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<meta property=\"og:locale\" content=\"en_GB\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Alexandre Proutiere &#8212; Digital Futures\" \/>\n<meta property=\"og:description\" content=\"Data-efficient Reinforcement Learning\" \/>\n<meta property=\"og:url\" content=\"https:\/\/wpmu-tris.sys.kth.se\/digitalfutures\/research\/digital-futures-fellows\/alexandre-proutiere\/\" \/>\n<meta property=\"og:site_name\" content=\"Digital Futures\" \/>\n<meta property=\"article:modified_time\" content=\"2022-08-09T07:59:38+00:00\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Estimated reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"1 minute\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/wpmu-tris.sys.kth.se\\\/digitalfutures\\\/research\\\/digital-futures-fellows\\\/alexandre-proutiere\\\/\",\"url\":\"https:\\\/\\\/wpmu-tris.sys.kth.se\\\/digitalfutures\\\/research\\\/digital-futures-fellows\\\/alexandre-proutiere\\\/\",\"name\":\"Alexandre Proutiere &#8212; Digital Futures\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/wpmu-tris.sys.kth.se\\\/digitalfutures\\\/#website\"},\"datePublished\":\"2021-12-02T12:15:04+00:00\",\"dateModified\":\"2022-08-09T07:59:38+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/wpmu-tris.sys.kth.se\\\/digitalfutures\\\/research\\\/digital-futures-fellows\\\/alexandre-proutiere\\\/#breadcrumb\"},\"inLanguage\":\"en-GB\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/wpmu-tris.sys.kth.se\\\/digitalfutures\\\/research\\\/digital-futures-fellows\\\/alexandre-proutiere\\\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/wpmu-tris.sys.kth.se\\\/digitalfutures\\\/research\\\/digital-futures-fellows\\\/alexandre-proutiere\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/wpmu-tris.sys.kth.se\\\/digitalfutures\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Research\",\"item\":\"https:\\\/\\\/wpmu-tris.sys.kth.se\\\/digitalfutures\\\/research\\\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"Digital Futures Fellows\",\"item\":\"https:\\\/\\\/wpmu-tris.sys.kth.se\\\/digitalfutures\\\/research\\\/digital-futures-fellows\\\/\"},{\"@type\":\"ListItem\",\"position\":4,\"name\":\"Alexandre Proutiere\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/wpmu-tris.sys.kth.se\\\/digitalfutures\\\/#website\",\"url\":\"https:\\\/\\\/wpmu-tris.sys.kth.se\\\/digitalfutures\\\/\",\"name\":\"Digital Futures\",\"description\":\"\",\"publisher\":{\"@id\":\"https:\\\/\\\/wpmu-tris.sys.kth.se\\\/digitalfutures\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/wpmu-tris.sys.kth.se\\\/digitalfutures\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-GB\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/wpmu-tris.sys.kth.se\\\/digitalfutures\\\/#organization\",\"name\":\"Digital Futures\",\"url\":\"https:\\\/\\\/wpmu-tris.sys.kth.se\\\/digitalfutures\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-GB\",\"@id\":\"https:\\\/\\\/wpmu-tris.sys.kth.se\\\/digitalfutures\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"\\\/wp-content\\\/uploads\\\/sites\\\/7\\\/2020\\\/11\\\/df_black_hires.png\",\"contentUrl\":\"\\\/wp-content\\\/uploads\\\/sites\\\/7\\\/2020\\\/11\\\/df_black_hires.png\",\"width\":5870,\"height\":856,\"caption\":\"Digital Futures\"},\"image\":{\"@id\":\"https:\\\/\\\/wpmu-tris.sys.kth.se\\\/digitalfutures\\\/#\\\/schema\\\/logo\\\/image\\\/\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Alexandre Proutiere &#8212; Digital Futures","robots":{"index":"noindex","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"og_locale":"en_GB","og_type":"article","og_title":"Alexandre Proutiere &#8212; Digital Futures","og_description":"Data-efficient Reinforcement Learning","og_url":"https:\/\/wpmu-tris.sys.kth.se\/digitalfutures\/research\/digital-futures-fellows\/alexandre-proutiere\/","og_site_name":"Digital Futures","article_modified_time":"2022-08-09T07:59:38+00:00","twitter_card":"summary_large_image","twitter_misc":{"Estimated reading time":"1 minute"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/wpmu-tris.sys.kth.se\/digitalfutures\/research\/digital-futures-fellows\/alexandre-proutiere\/","url":"https:\/\/wpmu-tris.sys.kth.se\/digitalfutures\/research\/digital-futures-fellows\/alexandre-proutiere\/","name":"Alexandre Proutiere &#8212; Digital Futures","isPartOf":{"@id":"https:\/\/wpmu-tris.sys.kth.se\/digitalfutures\/#website"},"datePublished":"2021-12-02T12:15:04+00:00","dateModified":"2022-08-09T07:59:38+00:00","breadcrumb":{"@id":"https:\/\/wpmu-tris.sys.kth.se\/digitalfutures\/research\/digital-futures-fellows\/alexandre-proutiere\/#breadcrumb"},"inLanguage":"en-GB","potentialAction":[{"@type":"ReadAction","target":["https:\/\/wpmu-tris.sys.kth.se\/digitalfutures\/research\/digital-futures-fellows\/alexandre-proutiere\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/wpmu-tris.sys.kth.se\/digitalfutures\/research\/digital-futures-fellows\/alexandre-proutiere\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/wpmu-tris.sys.kth.se\/digitalfutures\/"},{"@type":"ListItem","position":2,"name":"Research","item":"https:\/\/wpmu-tris.sys.kth.se\/digitalfutures\/research\/"},{"@type":"ListItem","position":3,"name":"Digital Futures Fellows","item":"https:\/\/wpmu-tris.sys.kth.se\/digitalfutures\/research\/digital-futures-fellows\/"},{"@type":"ListItem","position":4,"name":"Alexandre Proutiere"}]},{"@type":"WebSite","@id":"https:\/\/wpmu-tris.sys.kth.se\/digitalfutures\/#website","url":"https:\/\/wpmu-tris.sys.kth.se\/digitalfutures\/","name":"Digital Futures","description":"","publisher":{"@id":"https:\/\/wpmu-tris.sys.kth.se\/digitalfutures\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/wpmu-tris.sys.kth.se\/digitalfutures\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-GB"},{"@type":"Organization","@id":"https:\/\/wpmu-tris.sys.kth.se\/digitalfutures\/#organization","name":"Digital Futures","url":"https:\/\/wpmu-tris.sys.kth.se\/digitalfutures\/","logo":{"@type":"ImageObject","inLanguage":"en-GB","@id":"https:\/\/wpmu-tris.sys.kth.se\/digitalfutures\/#\/schema\/logo\/image\/","url":"\/wp-content\/uploads\/sites\/7\/2020\/11\/df_black_hires.png","contentUrl":"\/wp-content\/uploads\/sites\/7\/2020\/11\/df_black_hires.png","width":5870,"height":856,"caption":"Digital Futures"},"image":{"@id":"https:\/\/wpmu-tris.sys.kth.se\/digitalfutures\/#\/schema\/logo\/image\/"}}]}},"_links":{"self":[{"href":"https:\/\/wpmu-tris.sys.kth.se\/digitalfutures\/wp-json\/wp\/v2\/pages\/6626","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/wpmu-tris.sys.kth.se\/digitalfutures\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/wpmu-tris.sys.kth.se\/digitalfutures\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/wpmu-tris.sys.kth.se\/digitalfutures\/wp-json\/wp\/v2\/users\/46"}],"replies":[{"embeddable":true,"href":"https:\/\/wpmu-tris.sys.kth.se\/digitalfutures\/wp-json\/wp\/v2\/comments?post=6626"}],"version-history":[{"count":7,"href":"https:\/\/wpmu-tris.sys.kth.se\/digitalfutures\/wp-json\/wp\/v2\/pages\/6626\/revisions"}],"predecessor-version":[{"id":9474,"href":"https:\/\/wpmu-tris.sys.kth.se\/digitalfutures\/wp-json\/wp\/v2\/pages\/6626\/revisions\/9474"}],"up":[{"embeddable":true,"href":"https:\/\/wpmu-tris.sys.kth.se\/digitalfutures\/wp-json\/wp\/v2\/pages\/6563"}],"wp:attachment":[{"href":"https:\/\/wpmu-tris.sys.kth.se\/digitalfutures\/wp-json\/wp\/v2\/media?parent=6626"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}