How Google's AI is teaching itself to play computer games like a human - Tech Insider (blog) [Archive]

RetromanIE

10-02-2016, 03:37

<table border="0" cellpadding="2" cellspacing="7" style="vertical-align:top;"><tr><td width="80" align="center" valign="top"><a href="http://news.google.com/news/url?sa=t&fd=R&ct2=en_ie&usg=AFQjCNGB2PrEaSdTelMuuB6XAygnWu21Wg&clid=c3a7d30bb8a4878e06b80cf16b898331&ei=ob66Vsj_Icio1QbpnpOYDw&url=http://www.techinsider.io/google-deepmind-uses-ai-to-navigate-maze-race-cars-2016-2"><img src="//t1.gstatic.com/images?q=tbn:ANd9GcTpiC1BtcxcKaWjmxZz_uBvemIU3AeKM GdADOm3tkUPm0c_93x7twVFhRVUBjyjBsy9GlJ42_J5" alt="" border="1" width="80" height="80"> Tech Insider (blog)</a></td><td valign="top" class="j"> <div style="padding-top:0.8em;"><img alt="" height="1" width="1"></div><div class="lh"><a href="http://news.google.com/news/url?sa=t&fd=R&ct2=en_ie&usg=AFQjCNGB2PrEaSdTelMuuB6XAygnWu21Wg&clid=c3a7d30bb8a4878e06b80cf16b898331&ei=ob66Vsj_Icio1QbpnpOYDw&url=http://www.techinsider.io/google-deepmind-uses-ai-to-navigate-maze-race-cars-2016-2">How Google's AI is teaching itself to play computer games like a human</a> Tech Insider (blog) Reinforcement learning is when AI is rewarded for taking steps to improve its score. Combining this technique with a deep neural network, which is when the AI analyzes and learns patterns on the game screen, allowed DeepMind to master the Atari games. <a class="p" href="http://news.google.ie/news/more?ncl=dQ05-e7Q_NFm90M&authuser=0&ned=en_ie"></a></div></td></tr></table>

More... (http://news.google.com/news/url?sa=t&fd=R&ct2=en_ie&usg=AFQjCNGB2PrEaSdTelMuuB6XAygnWu21Wg&clid=c3a7d30bb8a4878e06b80cf16b898331&ei=ob66Vsj_Icio1QbpnpOYDw&url=http://www.techinsider.io/google-deepmind-uses-ai-to-navigate-maze-race-cars-2016-2)