{"id":3896,"date":"2015-02-25T18:27:53","date_gmt":"2015-02-25T23:27:53","guid":{"rendered":"http:\/\/sciencemediacentre.ca\/site\/?p=3896"},"modified":"2015-02-25T18:27:53","modified_gmt":"2015-02-25T23:27:53","slug":"machine-intelligence-beats-classic-video-games","status":"publish","type":"post","link":"http:\/\/sciencemediacentre.ca\/site\/machine-intelligence-beats-classic-video-games\/","title":{"rendered":"Machine intelligence beats classic video games"},"content":{"rendered":"<p><a href=\"http:\/\/sciencemediacentre.ca\/site\/wp-content\/uploads\/2013\/12\/SMCC-english2.jpg\"><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter size-full wp-image-110\" src=\"http:\/\/sciencemediacentre.ca\/site\/wp-content\/uploads\/2013\/12\/SMCC-english2.jpg\" alt=\"SMCC-english2\" width=\"255\" height=\"126\" \/><\/a><\/p>\n<p>A new artificial intelligence program learned how to play 49 classic arcade video games (such as Pong, Breakout, Space Invaders and Asteroids) when given only minimal information, a new study shows.<\/p>\n<p>The program was able to surpass the performance of all previous algorithms and outperformed a professional human games tester in a majority of the games.<\/p>\n<p>The authors conclude that this study will help scientists program artificial intelligence systems that will learn to perform various challenging tasks from scratch.<\/p>\n<p>Videos of the program playing <a href=\"https:\/\/www.youtube.com\/watch?v=cjpEIotvwFY\" target=\"_blank\"><span style=\"text-decoration: underline;\">Breakout<\/span><\/a> and <span style=\"text-decoration: underline;\"><a href=\"https:\/\/www.youtube.com\/watch?v=Dds_yDJFhvI\" target=\"_blank\">Space Invaders<\/a><\/span> are available.<\/p>\n<p><a href=\"http:\/\/www.nature.com\/srep\/2015\/150212\/srep08481\/full\/srep08481.html\" target=\"_blank\"><span style=\"text-decoration: underline;\">Original research paper<\/span><\/a>\u00a0published in <em>Nature\u00a0<\/em>on\u00a0<strong>February 25<\/strong><span class=\"aBn\" tabindex=\"0\" data-term=\"goog_453723367\"><span class=\"aQJ\"><strong>, 2015<\/strong>.<\/span><\/span><\/p>\n<p><span style=\"text-decoration: underline;\"><em><strong>Names and affiliations of selected\u00a0authors<\/strong><\/em><\/span><\/p>\n<h4>Demis Hassabis, Google DeepMind, London, United Kingdom<\/h4>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>A new artificial intelligence program learned how to play 49 classic arcade video games (such as Pong, Breakout, Space Invaders and Asteroids) when given only minimal information, a new study shows. The program was able to surpass the performance of all previous algorithms and outperformed a professional human games tester in a majority of the [&hellip;]<\/p>\n","protected":false},"author":3,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_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":""},"categories":[25],"tags":[2374,1011,2238],"class_list":["post-3896","post","type-post","status-publish","format-standard","hentry","category-paper-of-interest","tag-computers","tag-technology","tag-video-games"],"jetpack_featured_media_url":"","jetpack_shortlink":"https:\/\/wp.me\/p4DqbN-10Q","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"http:\/\/sciencemediacentre.ca\/site\/wp-json\/wp\/v2\/posts\/3896","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/sciencemediacentre.ca\/site\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/sciencemediacentre.ca\/site\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/sciencemediacentre.ca\/site\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"http:\/\/sciencemediacentre.ca\/site\/wp-json\/wp\/v2\/comments?post=3896"}],"version-history":[{"count":1,"href":"http:\/\/sciencemediacentre.ca\/site\/wp-json\/wp\/v2\/posts\/3896\/revisions"}],"predecessor-version":[{"id":3899,"href":"http:\/\/sciencemediacentre.ca\/site\/wp-json\/wp\/v2\/posts\/3896\/revisions\/3899"}],"wp:attachment":[{"href":"http:\/\/sciencemediacentre.ca\/site\/wp-json\/wp\/v2\/media?parent=3896"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/sciencemediacentre.ca\/site\/wp-json\/wp\/v2\/categories?post=3896"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/sciencemediacentre.ca\/site\/wp-json\/wp\/v2\/tags?post=3896"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}