<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
		>
<channel>
	<title>Comments on: Programming Poker AI</title>
	<atom:link href="http://cowboyprogramming.com/2007/01/04/programming-poker-ai/feed/" rel="self" type="application/rss+xml" />
	<link>http://cowboyprogramming.com/2007/01/04/programming-poker-ai/</link>
	<description>Game Development and General Hacking by the Old West</description>
	<lastBuildDate>Tue, 20 Jul 2010 15:03:31 +0000</lastBuildDate>
	<generator>http://wordpress.org/?v=2.9.1</generator>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
		<item>
		<title>By: EastZoneSoupCube - links for 2010-07-20</title>
		<link>http://cowboyprogramming.com/2007/01/04/programming-poker-ai/comment-page-1/#comment-172372</link>
		<dc:creator>EastZoneSoupCube - links for 2010-07-20</dc:creator>
		<pubDate>Tue, 20 Jul 2010 15:03:31 +0000</pubDate>
		<guid isPermaLink="false">http://cowboyprogramming.com/?p=25#comment-172372</guid>
		<description>[...] Cowboy Programming » Programming Poker AI I recently programmed the AI for the World Series of Poker, developed by Left Field Productions and published by Activision. I started out thinking it would be an easy task. But it proved a lot more complex than I initially thought. (tags: algorithm AI programming machine learning development) [...]</description>
		<content:encoded><![CDATA[<p>[...] Cowboy Programming » Programming Poker AI I recently programmed the AI for the World Series of Poker, developed by Left Field Productions and published by Activision. I started out thinking it would be an easy task. But it proved a lot more complex than I initially thought. (tags: algorithm AI programming machine learning development) [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Cowboy Programming » Programming Poker AI : Popular Links : eConsultant</title>
		<link>http://cowboyprogramming.com/2007/01/04/programming-poker-ai/comment-page-1/#comment-172064</link>
		<dc:creator>Cowboy Programming » Programming Poker AI : Popular Links : eConsultant</dc:creator>
		<pubDate>Sun, 18 Jul 2010 22:22:26 +0000</pubDate>
		<guid isPermaLink="false">http://cowboyprogramming.com/?p=25#comment-172064</guid>
		<description>[...] the rest here: Cowboy Programming » Programming Poker AI   23 March 2010  &#124; Uncategorized &#124; Trackback &#124; del.icio.us &#124; Stumble it! &#124; View Count : 0  Next [...]</description>
		<content:encoded><![CDATA[<p>[...] the rest here: Cowboy Programming » Programming Poker AI   23 March 2010  | Uncategorized | Trackback | del.icio.us | Stumble it! | View Count : 0  Next [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Poker Bill</title>
		<link>http://cowboyprogramming.com/2007/01/04/programming-poker-ai/comment-page-1/#comment-149153</link>
		<dc:creator>Poker Bill</dc:creator>
		<pubDate>Thu, 11 Feb 2010 07:46:44 +0000</pubDate>
		<guid isPermaLink="false">http://cowboyprogramming.com/?p=25#comment-149153</guid>
		<description>Very cool article, thanks.  I&#039;m a Flash games developer and I&#039;ve looked into the idea of building a multi-player Holdem game using something like Electroserver or SmartFox server in the past, but I&#039;d only ever considered it in terms of a multiplayer game.  Now the idea of building a one player game with AI players sounds like a fun idea.</description>
		<content:encoded><![CDATA[<p>Very cool article, thanks.  I&#8217;m a Flash games developer and I&#8217;ve looked into the idea of building a multi-player Holdem game using something like Electroserver or SmartFox server in the past, but I&#8217;d only ever considered it in terms of a multiplayer game.  Now the idea of building a one player game with AI players sounds like a fun idea.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: personalized playing cards</title>
		<link>http://cowboyprogramming.com/2007/01/04/programming-poker-ai/comment-page-1/#comment-147366</link>
		<dc:creator>personalized playing cards</dc:creator>
		<pubDate>Tue, 26 Jan 2010 14:55:08 +0000</pubDate>
		<guid isPermaLink="false">http://cowboyprogramming.com/?p=25#comment-147366</guid>
		<description>I am currently working on a php game for the poker. Your article really helps a lot. thanks! :)</description>
		<content:encoded><![CDATA[<p>I am currently working on a php game for the poker. Your article really helps a lot. thanks! :)</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Erick</title>
		<link>http://cowboyprogramming.com/2007/01/04/programming-poker-ai/comment-page-1/#comment-138929</link>
		<dc:creator>Erick</dc:creator>
		<pubDate>Sat, 28 Nov 2009 12:11:05 +0000</pubDate>
		<guid isPermaLink="false">http://cowboyprogramming.com/?p=25#comment-138929</guid>
		<description>Thanks for the tip on the Knuth algo! That&#039;s helpful for our research.</description>
		<content:encoded><![CDATA[<p>Thanks for the tip on the Knuth algo! That&#8217;s helpful for our research.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Phil Ivey</title>
		<link>http://cowboyprogramming.com/2007/01/04/programming-poker-ai/comment-page-1/#comment-136706</link>
		<dc:creator>Phil Ivey</dc:creator>
		<pubDate>Fri, 06 Nov 2009 09:33:19 +0000</pubDate>
		<guid isPermaLink="false">http://cowboyprogramming.com/?p=25#comment-136706</guid>
		<description>Remember the AI player is also the dealer. Another approach to AI would be to simply let him cheat. He knows what cards everyone is holding and what the community cards will be. 

Also, for anyone considering writing a poker game, lookup the Knuth shuffle algorithm. If you take a naive approach to dealing cards your simulations will give the wrong results</description>
		<content:encoded><![CDATA[<p>Remember the AI player is also the dealer. Another approach to AI would be to simply let him cheat. He knows what cards everyone is holding and what the community cards will be. </p>
<p>Also, for anyone considering writing a poker game, lookup the Knuth shuffle algorithm. If you take a naive approach to dealing cards your simulations will give the wrong results</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Poker guy</title>
		<link>http://cowboyprogramming.com/2007/01/04/programming-poker-ai/comment-page-1/#comment-135900</link>
		<dc:creator>Poker guy</dc:creator>
		<pubDate>Sat, 31 Oct 2009 07:24:13 +0000</pubDate>
		<guid isPermaLink="false">http://cowboyprogramming.com/?p=25#comment-135900</guid>
		<description>I notice that a number of people are saying that they would like to work in AI which is the same situation I am in. I literally have no experience with data extraction or stealthing.. If there was a collaborative effort being started, I would certainly be interested in getting involved.</description>
		<content:encoded><![CDATA[<p>I notice that a number of people are saying that they would like to work in AI which is the same situation I am in. I literally have no experience with data extraction or stealthing.. If there was a collaborative effort being started, I would certainly be interested in getting involved.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: WSOP</title>
		<link>http://cowboyprogramming.com/2007/01/04/programming-poker-ai/comment-page-1/#comment-134681</link>
		<dc:creator>WSOP</dc:creator>
		<pubDate>Mon, 19 Oct 2009 12:03:28 +0000</pubDate>
		<guid isPermaLink="false">http://cowboyprogramming.com/?p=25#comment-134681</guid>
		<description>I wonder how hard is it program a poker bot. I mean it shouldn&#039;t be too hard in microlimits with lots of fish. All you have to do is sit and wait for a good hand and then raise. That way you wouldn&#039;t get into too many marginal hands after the flop, so you would have to use any complex algorithms to determine, whether you should check/call/raise/fold.

The bot would only play top pairs starting at JJ and AK preflop.

Mick, I would very much like to get your opionion on this.</description>
		<content:encoded><![CDATA[<p>I wonder how hard is it program a poker bot. I mean it shouldn&#8217;t be too hard in microlimits with lots of fish. All you have to do is sit and wait for a good hand and then raise. That way you wouldn&#8217;t get into too many marginal hands after the flop, so you would have to use any complex algorithms to determine, whether you should check/call/raise/fold.</p>
<p>The bot would only play top pairs starting at JJ and AK preflop.</p>
<p>Mick, I would very much like to get your opionion on this.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Steven</title>
		<link>http://cowboyprogramming.com/2007/01/04/programming-poker-ai/comment-page-1/#comment-128661</link>
		<dc:creator>Steven</dc:creator>
		<pubDate>Mon, 24 Aug 2009 05:42:24 +0000</pubDate>
		<guid isPermaLink="false">http://cowboyprogramming.com/?p=25#comment-128661</guid>
		<description>Wow! I used to play that game all the time back then, before i had the net.

I remember going super aggressive versus the AI seemed to be the best way to go since I would get schooled playing passive.

Although, I suppose that&#039;s the same as real life eh?</description>
		<content:encoded><![CDATA[<p>Wow! I used to play that game all the time back then, before i had the net.</p>
<p>I remember going super aggressive versus the AI seemed to be the best way to go since I would get schooled playing passive.</p>
<p>Although, I suppose that&#8217;s the same as real life eh?</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Mick West</title>
		<link>http://cowboyprogramming.com/2007/01/04/programming-poker-ai/comment-page-1/#comment-118833</link>
		<dc:creator>Mick West</dc:creator>
		<pubDate>Sat, 27 Jun 2009 21:43:40 +0000</pubDate>
		<guid isPermaLink="false">http://cowboyprogramming.com/?p=25#comment-118833</guid>
		<description>The simplest way is, instead of having these two hand types enums:

E_STRAIGHT
E_STRAIGHTFLUSH

have four

E_STRAIGHT_ACELOW
E_STRAIGHT_ACEHIGH
E_STRAIGHTFLUSH_ACELOW
E_STRAIGHTFLUSH_ACEHIGH

Then you just a have a small amount of special case coding to determine the type, and the comparison will resolve itself (as E_STRAIGHT_ACEHIGH &gt; E_STRAIGHT_ACELOW)

This is the value that goes in the &quot;Type&quot; nibble in the diagram above.</description>
		<content:encoded><![CDATA[<p>The simplest way is, instead of having these two hand types enums:</p>
<p>E_STRAIGHT<br />
E_STRAIGHTFLUSH</p>
<p>have four</p>
<p>E_STRAIGHT_ACELOW<br />
E_STRAIGHT_ACEHIGH<br />
E_STRAIGHTFLUSH_ACELOW<br />
E_STRAIGHTFLUSH_ACEHIGH</p>
<p>Then you just a have a small amount of special case coding to determine the type, and the comparison will resolve itself (as E_STRAIGHT_ACEHIGH > E_STRAIGHT_ACELOW)</p>
<p>This is the value that goes in the &#8220;Type&#8221; nibble in the diagram above.</p>
]]></content:encoded>
	</item>
</channel>
</rss>

<!-- Dynamic Page Served (once) in 0.571 seconds -->
