{"id":160245,"date":"2023-03-14T08:22:17","date_gmt":"2023-03-14T13:22:17","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2023\/03\/an-ai-learned-to-play-atari-6000-times-faster"},"modified":"2023-03-14T08:22:17","modified_gmt":"2023-03-14T13:22:17","slug":"an-ai-learned-to-play-atari-6000-times-faster","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2023\/03\/an-ai-learned-to-play-atari-6000-times-faster","title":{"rendered":"An AI Learned to Play Atari 6,000 Times Faster"},"content":{"rendered":"<p><\/a><\/p>\n<p><iframe loading=\"lazy\" title=\"Wanderers - a short film by Erik Wernquist\" src=\"https:\/\/player.vimeo.com\/video\/108650530?dnt=1&amp;app_id=122963\" width=\"640\" height=\"272\" frameborder=\"0\" allow=\"autoplay; fullscreen; picture-in-picture; clipboard-write; encrypted-media\"><\/iframe><\/p>\n<p>We don\u2019t learn by brute force repetition. AI shouldn\u2019t either.<\/p>\n<hr>\n<p>Despite impressive progress, today\u2019s AI models are very <a href=\"https:\/\/singularityhub.com\/2019\/06\/26\/making-algorithms-more-like-kids-what-can-four-year-olds-do-that-ai-cant\/\">inefficient learners<\/a>, taking huge amounts of time and data to solve problems humans pick up almost instantaneously. A new approach could drastically speed things up by getting AI to read instruction manuals before attempting a challenge.<\/p>\n<p>One of the most promising approaches to creating AI that can solve a diverse range of problems is reinforcement learning, which involves setting a goal and rewarding the AI for taking actions that work towards that goal. This is the approach behind most of the major breakthroughs in game-playing AI, such as DeepMind\u2019s AlphaGo.<\/p>\n<p>As powerful as the technique is, it essentially relies on trial and error to find an effective strategy. This means these algorithms can spend the equivalent of several years blundering through video and board games until they hit on a winning formula.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>We don\u2019t learn by brute force repetition. AI shouldn\u2019t either. Despite impressive progress, today\u2019s AI models are very inefficient learners, taking huge amounts of time and data to solve problems humans pick up almost instantaneously. A new approach could drastically speed things up by getting AI to read instruction manuals before attempting a challenge. One [\u2026]<\/p>\n","protected":false},"author":672,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[41,6],"tags":[],"class_list":["post-160245","post","type-post","status-publish","format-standard","hentry","category-information-science","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/160245","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/users\/672"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=160245"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/160245\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=160245"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=160245"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=160245"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}