Human-level control through deep reinforcement learning - Nature.com

[RetromanIE]

<table border="0" cellpadding="2" cellspacing="7" style="vertical-align:top;"><tr><td width="80" align="center" valign="top"><font style="font-size:85%;font-family:arial,sans-serif"><a href="http://news.google.com/news/url?sa=t&fd=R&ct2=en_ie&usg=AFQjCNF7PRCbAPCOgxRVuyVQrAKj0vogOA&clid=c3a7d30bb8a4878e06b80cf16b898331&ei=_rnwVOjZOO-NiwaGqoDAAg&url=http://www.nature.com/nature/journal/v518/n7540/full/nature14236.html"><img src="//t3.gstatic.com/images?q=tbn:ANd9GcRbsgU2paJ_dloQ-ILGqid3xK7pmWUtOaC4wYyJYd7PmdBxbqYv9Ef4FXqFp2UNYFT 4y6TiIkk" alt="" border="1" width="80" height="80"><br><font size="-2">Nature.com</font></a></font></td><td valign="top" class="j"><font style="font-size:85%;font-family:arial,sans-serif"><br><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=AFQjCNF7PRCbAPCOgxRVuyVQrAKj0vogOA&clid=c3a7d30bb8a4878e06b80cf16b898331&ei=_rnwVOjZOO-NiwaGqoDAAg&url=http://www.nature.com/nature/journal/v518/n7540/full/nature14236.html"><b>Human-level control through deep reinforcement learning</b></a><br><font size="-1"><b><font color="#6f6f6f">Nature.com</font></b></font><br><font size="-1">We tested this agent on the challenging domain of classic <b>Atari 2600</b> games¹². We demonstrate that the deep Q-network agent, receiving only the pixels and the game score as inputs, was able to surpass the performance of all previous algorithms and&nbsp;...</font><br><font size="-1" class="p"></font><br><font class="p" size="-1"><a class="p" href="http://news.google.ie/news/more?ncl=dnKzPAEf-lkyCnM&authuser=0&ned=en_ie"><nobr><b></b></nobr></a></font></div></font></td></tr></table>

More... (http://news.google.com/news/url?sa=t&fd=R&ct2=en_ie&usg=AFQjCNF7PRCbAPCOgxRVuyVQrAKj0vogOA&clid=c3a7d30bb8a4878e06b80cf16b898331&ei=_rnwVOjZOO-NiwaGqoDAAg&url=http://www.nature.com/nature/journal/v518/n7540/full/nature14236.html)