<node id="501841">
  <nid>501841</nid>
  <type>external_news</type>
  <uid>
    <user id="28466"><![CDATA[28466]]></user>
  </uid>
  <created>1455714873</created>
  <changed>1475893678</changed>
  <title><![CDATA[How Computers Learned to Play Nintendo]]></title>
  <body><![CDATA[<p>One group sponsored an annual Mario AI competition, Jordan Pearson reports for Motherboard, and a pair of Georgia Tech computer scientists named Mark Riedl and Matthew Guzdial have even built an AI that can design Super Mario Bros. levels from scratch. "It is a bit more fast-paced and dynamic than the Atari games that many are currently using to test AI," Riedl and Guzdial tell Pearson. "The side-scrolling nature of the game means a lot of the game is unobservable to the AI, whereas many simpler arcade games have all information on screen at once."</p><p>Read the full article here:&nbsp;<a title="http://www.smithsonianmag.com/smart-news/how-computers-learned-to-play-nintendo-180957125/?no-ist" href="http://www.smithsonianmag.com/smart-news/how-computers-learned-to-play-nintendo-180957125/?no-ist">http://www.smithsonianmag.com/smart-news/how-computers-learned-to-play-nintendo-180957125/?no-ist</a></p>]]></body>
  <field_article_url>
    <item>
      <url><![CDATA[http://www.smithsonianmag.com/smart-news/how-computers-learned-to-play-nintendo-180957125/?no-ist]]></url>
      <title><![CDATA[]]></title>
    </item>
  </field_article_url>
  <field_publication>
    <item>
      <value><![CDATA[ Summer College Research Internship ]]></value>
    </item>
  </field_publication>
  <field_dateline>
    <item>
      <value>2015-11-03</value>
      <timezone></timezone>
    </item>
  </field_dateline>
  <field_media>
        </field_media>
  <og_groups>
          <item>1299</item>
      </og_groups>
  <og_groups_both>
          <item><![CDATA[GVU Center]]></item>
      </og_groups_both>
    <field_userdata>
      <![CDATA[]]>
  </field_userdata>
</node>
