{"id":600,"date":"2025-04-04T01:00:26","date_gmt":"2025-04-04T05:00:26","guid":{"rendered":"https:\/\/www.notexponential.com\/notes\/?page_id=600"},"modified":"2025-04-04T01:02:48","modified_gmt":"2025-04-04T05:02:48","slug":"lecture-8-reinforcement-learning","status":"publish","type":"page","link":"https:\/\/www.notexponential.com\/notes\/artificial-intelligence\/lectures\/lecture-8-reinforcement-learning\/","title":{"rendered":"Lecture 8 &#8211; Reinforcement Learning"},"content":{"rendered":"\n<h2 class=\"wp-block-heading\">10 Minute Introductory Video, start here.<\/h2>\n\n\n\n<figure class=\"wp-block-embed is-type-video is-provider-youtube wp-block-embed-youtube wp-embed-aspect-4-3 wp-has-aspect-ratio\"><div class=\"wp-block-embed__wrapper\">\n<iframe loading=\"lazy\" title=\"Reinforcement Learning - 10 Minute Explainer\" width=\"625\" height=\"469\" src=\"https:\/\/www.youtube.com\/embed\/IeqfFa1czrQ?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" allowfullscreen><\/iframe>\n<\/div><\/figure>\n\n\n\n<p><\/p>\n\n\n\n<div style=\"height:100px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<h2 class=\"wp-block-heading\">Advanced Topics &#8211; Exploration vs. Exploitation<\/h2>\n\n\n\n<figure class=\"wp-block-embed is-type-video is-provider-youtube wp-block-embed-youtube wp-embed-aspect-4-3 wp-has-aspect-ratio\"><div class=\"wp-block-embed__wrapper\">\n<iframe loading=\"lazy\" title=\"Reinforcement Learning Advanced Topics\" width=\"625\" height=\"469\" src=\"https:\/\/www.youtube.com\/embed\/H_i9lmmVAno?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" allowfullscreen><\/iframe>\n<\/div><\/figure>\n\n\n\n<div style=\"height:100px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<h2 class=\"wp-block-heading\">Full Slidedeck<\/h2>\n\n\n\n<div data-wp-interactive=\"core\/file\" class=\"wp-block-file\"><object data-wp-bind--hidden=\"!state.hasPdfPreview\" hidden class=\"wp-block-file__embed\" data=\"https:\/\/www.notexponential.com\/notes\/wp-content\/uploads\/2025\/04\/AI_T8_ReinfoLearning.pdf\" type=\"application\/pdf\" style=\"width:100%;height:600px\" aria-label=\"Embed of AI_T8_ReinfoLearning.\"><\/object><a id=\"wp-block-file--media-c3eb68e1-ec23-4caa-8267-a18f634c391e\" href=\"https:\/\/www.notexponential.com\/notes\/wp-content\/uploads\/2025\/04\/AI_T8_ReinfoLearning.pdf\">AI_T8_ReinfoLearning<\/a><a href=\"https:\/\/www.notexponential.com\/notes\/wp-content\/uploads\/2025\/04\/AI_T8_ReinfoLearning.pdf\" class=\"wp-block-file__button wp-element-button\" download aria-describedby=\"wp-block-file--media-c3eb68e1-ec23-4caa-8267-a18f634c391e\">Download<\/a><\/div>\n","protected":false},"excerpt":{"rendered":"<p>10 Minute Introductory Video, start here. Advanced Topics &#8211; Exploration vs. Exploitation Full Slidedeck<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":531,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-600","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/www.notexponential.com\/notes\/wp-json\/wp\/v2\/pages\/600","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.notexponential.com\/notes\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/www.notexponential.com\/notes\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/www.notexponential.com\/notes\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.notexponential.com\/notes\/wp-json\/wp\/v2\/comments?post=600"}],"version-history":[{"count":3,"href":"https:\/\/www.notexponential.com\/notes\/wp-json\/wp\/v2\/pages\/600\/revisions"}],"predecessor-version":[{"id":604,"href":"https:\/\/www.notexponential.com\/notes\/wp-json\/wp\/v2\/pages\/600\/revisions\/604"}],"up":[{"embeddable":true,"href":"https:\/\/www.notexponential.com\/notes\/wp-json\/wp\/v2\/pages\/531"}],"wp:attachment":[{"href":"https:\/\/www.notexponential.com\/notes\/wp-json\/wp\/v2\/media?parent=600"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}