{"id":759293,"date":"2020-05-22T09:04:36","date_gmt":"2020-05-22T13:04:36","guid":{"rendered":"https:\/\/www.prime-wow.com\/?p=759293"},"modified":"2020-05-22T09:04:36","modified_gmt":"2020-05-22T13:04:36","slug":"after-watching-50000-hours-of-pac-man-nvidias-ai-generated-a-playable-clone","status":"publish","type":"post","link":"https:\/\/www.prime-wow.com\/?p=759293","title":{"rendered":"After watching 50,000 hours of Pac-Man, Nvidia\u2019s AI generated a playable clone"},"content":{"rendered":"<div id=\"rss-wrap\">\n<figure class=\"intro-image intro-left\"><img decoding=\"async\" src=\"https:\/\/www.prime-wow.com\/wp-content\/uploads\/2020\/05\/nvidia-gamegan-pacman-800x460-1.png\" alt=\"To rebuild &lt;em&gt;Pac-Man&lt;\/em&gt;, you must watch a lot of &lt;em&gt;Pac-Man&lt;\/em&gt;.\" \/><\/p>\n<p class=\"caption\" style=\"font-size:0.8em\"><a href=\"https:\/\/cdn.arstechnica.net\/wp-content\/uploads\/2020\/05\/nvidia-gamegan-pacman.png\" class=\"enlarge-link\" data-height=\"723\" data-width=\"1258\">Enlarge<\/a> <span class=\"sep\">\/<\/span> To rebuild <em>Pac-Man<\/em>, you must watch a lot of <em>Pac-Man<\/em>. (credit: Nvidia \/ Bandai-Namco)<\/p>\n<\/figure>\n<div><a name=\"page-1\" \/><\/div>\n<p>You may be familiar with the Infinite Monkey Theorem, an oft-cited (and often incorrectly quoted) claim that thousands of monkeys could bang on thousands of typewriters and eventually produce a work of art equivalent to Williams Shakespeare. (Yes, <a href=\"https:\/\/www.youtube.com\/watch?v=loMEF18Ir4s\">Simpsons did it<\/a>.)<\/p>\n<p>This week, Nvidia confirms that it has taken this theory quite seriously with its own twist: an army of AI routines, dubbed GameGAN (short for &#8220;generative adversarial networks&#8221;), trained to build a playable video game from scratch. More precisely, they&#8217;ve chosen one of the industry&#8217;s biggest, most recognizable games, celebrating its 40th anniversary today: <em>Pac-Man<\/em>.<\/p>\n<p>If you&#8217;ve seen other farms of computers trained on existing games, this has usually come in the form of them <a href=\"https:\/\/arstechnica.com\/gadgets\/2019\/07\/deepmind-ai-takes-on-the-public-in-starcraft-ii-multiplayer\/\">learning how to\u00a0<em>play<\/em> the game in question<\/a>. After watching thousands of hours of a particular game and tracking the most successful moves and reactions in the course of a versus match, these AI routines can then control games, repeat and juggle thousands of strategies, and battle humans. (Sometimes <a href=\"https:\/\/arstechnica.com\/gaming\/2019\/04\/openai-bot-crushes-dota-2-champions-and-now-anyone-can-play-against-it\/\">the results go well for the computers<\/a>, but <a href=\"https:\/\/arstechnica.com\/information-technology\/2016\/03\/google-ai-begins-battle-with-humanitys-best-go-player-tonight\/\">not always<\/a>.)<\/p>\n<\/div>\n<p><a href=\"https:\/\/arstechnica.com\/?p=1678052#p3\">Read 10 remaining paragraphs<\/a> | <a href=\"https:\/\/arstechnica.com\/?p=1678052&amp;comments=1\">Comments<\/a><\/p>\n<div class=\"feedflare\">\n<a href=\"http:\/\/feeds.arstechnica.com\/~ff\/arstechnica\/index?a=zBpe_7C8DHE:gvvhuS2kEH0:V_sGLiPBpWU\"><img decoding=\"async\" src=\"\" border=\"0\" \/><\/a> <a href=\"http:\/\/feeds.arstechnica.com\/~ff\/arstechnica\/index?a=zBpe_7C8DHE:gvvhuS2kEH0:F7zBnMyn0Lo\"><img decoding=\"async\" src=\"\" border=\"0\" \/><\/a> <a href=\"http:\/\/feeds.arstechnica.com\/~ff\/arstechnica\/index?a=zBpe_7C8DHE:gvvhuS2kEH0:qj6IDK7rITs\"><img decoding=\"async\" src=\"\" border=\"0\" \/><\/a> <a href=\"http:\/\/feeds.arstechnica.com\/~ff\/arstechnica\/index?a=zBpe_7C8DHE:gvvhuS2kEH0:yIl2AUoC8zA\"><img decoding=\"async\" src=\"\" border=\"0\" \/><\/a>\n<\/div>\n<p>&#013;<br \/>\n&#013;<br \/>\nSource: Ars Technica &#8211; <a href=\"https:\/\/arstechnica.com\/?p=1678052\" target=\"_blank\" rel=\"noopener noreferrer\">After watching 50,000 hours of Pac-Man, Nvidia\u2019s AI generated a playable clone<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Enlarge \/ To rebuild Pac-Man, you must watch a lot of Pac-Man. (credit: Nvidia \/ Bandai-Namco) You may be familiar with the Infinite Monkey Theorem, an oft-cited (and often incorrectly quoted) claim that thousands of monkeys could bang on thousands &hellip; <a href=\"https:\/\/www.prime-wow.com\/?p=759293\">Continue reading <span class=\"meta-nav\">&rarr;<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":759294,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"ngg_post_thumbnail":0,"footnotes":""},"categories":[27,110],"tags":[73],"class_list":["post-759293","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ars-technica","category-unfiltered-rss","tag-ars-technica"],"_links":{"self":[{"href":"https:\/\/www.prime-wow.com\/index.php?rest_route=\/wp\/v2\/posts\/759293","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.prime-wow.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.prime-wow.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.prime-wow.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.prime-wow.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=759293"}],"version-history":[{"count":0,"href":"https:\/\/www.prime-wow.com\/index.php?rest_route=\/wp\/v2\/posts\/759293\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.prime-wow.com\/index.php?rest_route=\/wp\/v2\/media\/759294"}],"wp:attachment":[{"href":"https:\/\/www.prime-wow.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=759293"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.prime-wow.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=759293"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.prime-wow.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=759293"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}