{"id":2703,"date":"2022-01-08T15:53:00","date_gmt":"2022-01-08T14:53:00","guid":{"rendered":"http:\/\/hugoscurto.com\/?post_type=jetpack-portfolio&#038;p=2703"},"modified":"2025-11-12T21:22:12","modified_gmt":"2025-11-12T20:22:12","slug":"performing-with-deep-reinforcement-learning","status":"publish","type":"jetpack-portfolio","link":"https:\/\/hugoscurto.com\/fr\/portfolio\/performing-with-deep-reinforcement-learning\/","title":{"rendered":"musiquer l'apprentissage profond par renforcement"},"content":{"rendered":"<h6><span style=\"color: #f5fe75;\">Scurto, 2019\u20142022<\/span><br \/><span style=\"color: #f5fe75;\">reflexive essay, music, computer science<br \/><\/span><\/h6>\n<p>A research-creation with musicking and deep reinforcement learning. It builds on the scientific study of two AI models, an audio VAE and the <a href=\"https:\/\/hugoscurto.com\/portfolio\/co-explorer\/\"><em>Co-Explorer<\/em><\/a>, and on musical experiments led in the frame of the <em><a href=\"https:\/\/hugoscurto.com\/portfolio\/aego\/\">\u00e6go<\/a> <\/em>performance. I discuss how deep reinforcement learning can be seen as a form of sonic comprovisational agent, enabling to compose sound spaces and improvise through feedback. I then reflect on how this opened my performer&#8217;s expectations away from instrumental control of sound, to deepen my listening of sound, and learn spiritual unification with music.<\/p>\n<h6><strong><span style=\"color: #f5fe75;\">Year<\/span><\/strong><br \/>2019\u20142022<\/h6>\n<h6><strong><span style=\"color: #f5fe75;\">Credits<\/span><\/strong><br \/>The project was developed with Axel Chemla\u2014Romeu-Santos in collaboration with the <a href=\"https:\/\/ismm.ircam.fr\/\" target=\"_blank\" rel=\"noopener\">ISMM<\/a> and <a href=\"http:\/\/acids.ircam.fr\/\" target=\"_blank\" rel=\"noopener\">ACIDS<\/a> groups of <a href=\"http:\/\/ircam.fr\/\" target=\"_blank\" rel=\"noopener noreferrer\">IRCAM<\/a>, in the context of a PhD thesis at <a href=\"https:\/\/www.sorbonne-universite.fr\/\" target=\"_blank\" rel=\"noopener noreferrer\">Sorbonne Universit\u00e9<\/a>.<\/h6>\n<h6><strong><span style=\"color: #f5fe75;\">Publications<\/span><\/strong><br \/><a href=\"https:\/\/hugoscurto.com\/wp-content\/uploads\/2021\/03\/scurto2021machine_authorsversion-2.pdf\" target=\"_blank\" rel=\"noopener\">Chapter at LNCS Springer<\/a> (2021)<br \/><a href=\"https:\/\/hugoscurto.com\/wp-content\/uploads\/2022\/05\/scurto2022musicking.pdf\" target=\"_blank\" rel=\"noopener\">Paper at TENOR<\/a> (2022)<\/h6>\n\n\n<p class=\"jetpack-slideshow-noscript robots-nocontent\">Ce diaporama n\u00e9cessite JavaScript.<\/p><div id=\"gallery-2703-1-slideshow\" class=\"jetpack-slideshow-window jetpack-slideshow jetpack-slideshow-black\" data-trans=\"fade\" data-autostart=\"1\" data-gallery=\"[{&quot;src&quot;:&quot;https:\\\/\\\/i0.wp.com\\\/hugoscurto.com\\\/wp-content\\\/uploads\\\/2022\\\/01\\\/performing-deep-reinforcement-learning-rect-3-1.jpg?fit=1080%2C608\\u0026ssl=1&quot;,&quot;id&quot;:&quot;7163&quot;,&quot;title&quot;:&quot;performing-deep-reinforcement-learning-rect-3&quot;,&quot;alt&quot;:&quot;&quot;,&quot;caption&quot;:&quot;&quot;,&quot;itemprop&quot;:&quot;image&quot;},{&quot;src&quot;:&quot;https:\\\/\\\/i0.wp.com\\\/hugoscurto.com\\\/wp-content\\\/uploads\\\/2014\\\/09\\\/capture-de28099ecc81cran-2019-10-20-acc80-17.01.46-e1615998339644.png?fit=1796%2C768\\u0026ssl=1&quot;,&quot;id&quot;:&quot;3585&quot;,&quot;title&quot;:&quot;capture-de28099ecc81cran-2019-10-20-acc80-17.01.46-e1571583810482&quot;,&quot;alt&quot;:&quot;&quot;,&quot;caption&quot;:&quot;&quot;,&quot;itemprop&quot;:&quot;image&quot;}]\" itemscope itemtype=\"https:\/\/schema.org\/ImageGallery\"><\/div>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Scurto, 2019\u20142022reflexive essay, music, computer science A research-creation with musicking and deep reinforcement learning. It builds on the scientific study of two AI models, an audio VAE and the Co-Explorer, and on musical experiments led in the frame of the \u00e6go performance. I discuss how deep reinforcement learning can be seen as a form of [&hellip;]<\/p>\n","protected":false},"author":97209351,"featured_media":7163,"comment_status":"closed","ping_status":"closed","template":"","format":"standard","meta":{"_coblocks_attr":"","_coblocks_dimensions":"","_coblocks_responsive_height":"","_coblocks_accordion_ie_support":"","_crdt_document":"","advanced_seo_description":"","jetpack_seo_html_title":"","jetpack_seo_noindex":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":false,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"jetpack-portfolio-type":[173],"jetpack-portfolio-tag":[],"class_list":["post-2703","jetpack-portfolio","type-jetpack-portfolio","status-publish","format-standard","has-post-thumbnail","hentry","jetpack-portfolio-type-science"],"jetpack_publicize_connections":[],"jetpack_likes_enabled":false,"jetpack_sharing_enabled":false,"_links":{"self":[{"href":"https:\/\/hugoscurto.com\/fr\/wp-json\/wp\/v2\/jetpack-portfolio\/2703","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/hugoscurto.com\/fr\/wp-json\/wp\/v2\/jetpack-portfolio"}],"about":[{"href":"https:\/\/hugoscurto.com\/fr\/wp-json\/wp\/v2\/types\/jetpack-portfolio"}],"author":[{"embeddable":true,"href":"https:\/\/hugoscurto.com\/fr\/wp-json\/wp\/v2\/users\/97209351"}],"replies":[{"embeddable":true,"href":"https:\/\/hugoscurto.com\/fr\/wp-json\/wp\/v2\/comments?post=2703"}],"version-history":[{"count":47,"href":"https:\/\/hugoscurto.com\/fr\/wp-json\/wp\/v2\/jetpack-portfolio\/2703\/revisions"}],"predecessor-version":[{"id":8585,"href":"https:\/\/hugoscurto.com\/fr\/wp-json\/wp\/v2\/jetpack-portfolio\/2703\/revisions\/8585"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/hugoscurto.com\/fr\/wp-json\/wp\/v2\/media\/7163"}],"wp:attachment":[{"href":"https:\/\/hugoscurto.com\/fr\/wp-json\/wp\/v2\/media?parent=2703"}],"wp:term":[{"taxonomy":"jetpack-portfolio-type","embeddable":true,"href":"https:\/\/hugoscurto.com\/fr\/wp-json\/wp\/v2\/jetpack-portfolio-type?post=2703"},{"taxonomy":"jetpack-portfolio-tag","embeddable":true,"href":"https:\/\/hugoscurto.com\/fr\/wp-json\/wp\/v2\/jetpack-portfolio-tag?post=2703"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}