<?xml version="1.0" encoding="UTF-8" ?>
<?xml-stylesheet type="text/xsl" href="https://www.paradisesgarage.com:443/mcweb2/utility/FeedStylesheets/rss.xsl" media="screen"?><rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:slash="http://purl.org/rss/1.0/modules/slash/" xmlns:wfw="http://wellformedweb.org/CommentAPI/"><channel><title>Starcraft II</title><link>https://www.paradisesgarage.com:443/mcweb2/forums/333.aspx</link><description>Talk about Starcraft II: Wings of Liberty in here!</description><dc:language>en</dc:language><generator>CommunityServer 2008.5 SP1 (Build: 31106.3070)</generator><item><title>Starcraft 2 Zerg Build Optimizer</title><link>https://www.paradisesgarage.com:443/mcweb2/forums/thread/3484.aspx</link><pubDate>Tue, 02 Nov 2010 06:22:19 GMT</pubDate><guid isPermaLink="false">b2ff3ccb-892e-4ceb-9a77-e4f6e73f7f60:3484</guid><dc:creator>DarkAstraea</dc:creator><slash:comments>0</slash:comments><comments>https://www.paradisesgarage.com:443/mcweb2/forums/thread/3484.aspx</comments><wfw:commentRss>https://www.paradisesgarage.com:443/mcweb2/forums/commentrss.aspx?SectionID=333&amp;PostID=3484</wfw:commentRss><description>&lt;p&gt;&lt;blockquote&gt;&lt;div&gt;Jamie recommends a blog post from software engineer Louis Brandy explaining how using genetic algorithms to evaluate build orders in &lt;em&gt;StarCraft 2&lt;/em&gt; has led to some surprisingly powerful results. &lt;/p&gt;
&lt;p&gt;Quoting:
&amp;quot;One of the reasons build-order optimization is so important is that 
you can discover openings that &amp;#39;hard-counter&amp;#39; other openings. If I can 
get an army of N size into your base when you do opening X, you will 
always lose. ... a genetic algorithm
 is a type of optimization algorithm that tries to find optimal 
solutions using a method analogous to biologic evolution (to be 
specific: descent with modification &amp;amp; natural selection). Put 
simply, you take a &amp;#39;population&amp;#39; of initial build orders, evaluate them 
for fitness, and modify the population according to each element&amp;rsquo;s 
fitness. In other words, have the most successful reproduce. The 
program&amp;rsquo;s input is simply the desired game state. In practice, this 
means &amp;#39;make N units&amp;#39; to determine some rush build order (but it also 
allows for other types of builds, like make N workers with some 
defensive structures and a small army).&amp;quot;&lt;/div&gt;&lt;/blockquote&gt;&lt;/p&gt;
&lt;p&gt;[&lt;a target="_blank" href="http://lbrandy.com/blog/2010/11/using-genetic-algorithms-to-find-starcraft-2-build-orders/"&gt;Clickeh&lt;/a&gt;][&lt;a target="_blank" href="http://code.google.com/p/evolutionchamber/"&gt;Optimus Prime&lt;/a&gt;]&lt;/p&gt;
&lt;p&gt;This is an amazing program! A definite plus for the zerg!&lt;/p&gt;&lt;div style="clear:both;"&gt;&lt;/div&gt;</description></item></channel></rss>