{"id":3425,"date":"2015-03-07T21:32:56","date_gmt":"2015-03-07T20:32:56","guid":{"rendered":"https:\/\/users.cg.tuwien.ac.at\/zsolnai\/?p=3425"},"modified":"2015-03-08T13:18:22","modified_gmt":"2015-03-08T12:18:22","slug":"fun-with-deepminds-deep-q-learning","status":"publish","type":"post","link":"https:\/\/users.cg.tuwien.ac.at\/zsolnai\/fun-with-deepminds-deep-q-learning\/","title":{"rendered":"Fun with DeepMind&#8217;s Deep Q-learning"},"content":{"rendered":"<p style=\"text-align: justify;\">I have had an awful lot of fun with Google DeepMind&#8217;s Deep Q-learning algorithm. It plays Atari Breakout\u00a0solely based on relying the sensory input, and doesn&#8217;t know anything about the game when starting out.<\/p>\n<p style=\"text-align: center;\"><iframe loading=\"lazy\" src=\"\/\/www.youtube.com\/embed\/V1eYniJ0Rnk\" width=\"640\" height=\"360\" frameborder=\"0\" allowfullscreen=\"allowfullscreen\"><\/iframe><\/p>\n<p style=\"text-align: justify;\"><strong><a href=\"https:\/\/users.cg.tuwien.ac.at\/zsolnai\/wp\/wp-content\/uploads\/2015\/03\/train_agent.patch\" target=\"_blank\">I have also added a patch<\/a><\/strong>\u00a0to fix\u00a0the visualization when reloading a pre-trained network. The window will appear after the first evaluation batch is done (typically a few minutes).\u00a0<strong><a href=\"https:\/\/users.cg.tuwien.ac.at\/zsolnai\/wp\/wp-content\/uploads\/2015\/03\/run_gpu\" target=\"_blank\">This<\/a><\/strong>\u00a0configuration is able to\u00a0run <strong><a href=\"https:\/\/github.com\/kuz\/DeepMind-Atari-Deep-Q-Learner\" target=\"_blank\">Ilya Kuzovkin&#8217;s version<\/a><\/strong>\u00a0using less than 1GB VRAM.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>I have had an awful lot of fun with Google DeepMind&#8217;s Deep Q-learning algorithm. It plays Atari Breakout\u00a0solely based on relying the sensory input, and doesn&#8217;t know anything about the game when starting out. I have also added a patch\u00a0to fix\u00a0the visualization when reloading a pre-trained network. The window will appear after the first evaluation [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":2940,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"jetpack_post_was_ever_published":false,"_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[20],"tags":[143,141,140,139,144,142],"class_list":["post-3425","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news","tag-atari-breakout","tag-deep-learning","tag-deepmind","tag-google","tag-machine-learning","tag-reinforcement-learning"],"jetpack_publicize_connections":[],"jetpack_featured_media_url":"https:\/\/users.cg.tuwien.ac.at\/zsolnai\/wp\/wp-content\/uploads\/2014\/04\/lightbulb-icon.jpg","jetpack_shortlink":"https:\/\/wp.me\/p8ZWyD-Tf","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/users.cg.tuwien.ac.at\/zsolnai\/wp-json\/wp\/v2\/posts\/3425","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/users.cg.tuwien.ac.at\/zsolnai\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/users.cg.tuwien.ac.at\/zsolnai\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/users.cg.tuwien.ac.at\/zsolnai\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/users.cg.tuwien.ac.at\/zsolnai\/wp-json\/wp\/v2\/comments?post=3425"}],"version-history":[{"count":2,"href":"https:\/\/users.cg.tuwien.ac.at\/zsolnai\/wp-json\/wp\/v2\/posts\/3425\/revisions"}],"predecessor-version":[{"id":3428,"href":"https:\/\/users.cg.tuwien.ac.at\/zsolnai\/wp-json\/wp\/v2\/posts\/3425\/revisions\/3428"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/users.cg.tuwien.ac.at\/zsolnai\/wp-json\/wp\/v2\/media\/2940"}],"wp:attachment":[{"href":"https:\/\/users.cg.tuwien.ac.at\/zsolnai\/wp-json\/wp\/v2\/media?parent=3425"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/users.cg.tuwien.ac.at\/zsolnai\/wp-json\/wp\/v2\/categories?post=3425"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/users.cg.tuwien.ac.at\/zsolnai\/wp-json\/wp\/v2\/tags?post=3425"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}