• C++ Programming for Financial Engineering
    Highly recommended by thousands of MFE students. Covers essential C++ topics with applications to financial engineering. Learn more Join!
    Python for Finance with Intro to Data Science
    Gain practical understanding of Python to read, understand, and write professional Python code for your first day on the job. Learn more Join!
    An Intuition-Based Options Primer for FE
    Ideal for entry level positions interviews and graduate studies, specializing in options trading arbitrage and options valuation models. Learn more Join!

Poker Bots Invade Online Gambling

An interesting article from NYT. Makes good reading for many of our members who play poker and know a thing or two about poker bot.

Bryan Taylor, 36, could not shake the feeling that something funny was going on. Three of his most frequent opponents on an online poker site were acting oddly, playing in ways that were so similar it was suspicious.

Mr. Taylor, who started playing poker professionally in 2008, suspected that he was competing against computers — specifically bots, short for robots — that had been programmed to play poker and beat the odds.

And he was right. After an investigation, the site Mr. Taylor frequented, PokerStars, determined that his opponents had been computers masquerading as people and shut them down.

Poker bots are not new, but until recently they were not very good. Humans were better at the nuances of the game — at bluffing, for instance — and could routinely beat the machines. But artificial intelligence has come a long way in the last few years, far enough that poker bots are now good enough to win tens of thousands of dollars on major game sites, which are clamping down on them.

The bots that Mr. Taylor identified on PokerStars were shut down in July. In October, another large poker site, Full Tilt, informed customers that it had taken action to limit the proliferation of bots, including freezing some accounts. (Internet gambling is illegal in the United States, but online casinos operate offshore.)

“PokerStars is continuing to invest substantial resources to combat bots,” Michael Josem, a security manager at the site, said in an interview conducted via e-mail. “When a player is identified as a bot, PokerStars removes them from our games as soon as possible.” Their winnings are confiscated, he said, and the company will “provide compensation to players when appropriate.”

Yet poker bots are openly for sale online. Shanky Technologies sells licenses for the Holdem Poker Bot — the target of Full Tilt’s crackdown in October — for $129 per year. Brian Jetter, a co-founder of Shanky, said in an e-mail interview that more than 400 of his customers had been banned from Full Tilt. (Full Tilt did not respond to requests for comment.)

Mr. Jetter said that Full Tilt had seized more than $50,000 of his customers’ money, a figure that he called a “conservative estimate.” He added that the gaming site was forgoing at least $70,000 per month in revenue by shutting down his customers’ bots.

“They really must have wanted us gone,” Mr. Jetter said. “We don’t think the other poker rooms we support will make a similar financial decision.”

According to the Web site PokerScout.com, which bills itself as an Internet poker clearinghouse, there are more than 600 Web sites where people can play online. Mr. Jetter says that while Shanky does not have any “official relationships with the poker rooms,” some of them look the other way when bots play.

The science of poker bots is still in its infancy, which may be one reason that some gambling sites do not crack down on them. Unlike Watson, the I.B.M. computer that won on “Jeopardy!,” poker bots are not stellar players. But they are getting better, thanks to advances in the way computer scientists program software to play games.

“The large majority of bots are very bad,” said Darse Billings, a consultant to PokerStars and Full Tilt and the former chief of data analytics at Full Tilt. “More than 90 percent are losing money.”

It turns out to be a lot easier to build a perfect chess player than a poker whiz. Chess is a perfect information game: if you look at a chessboard, you know the exact state of the game from both players’ perspectives. And the rules of the game are not affected by chance, like the drawing of a card.

But in poker, an imperfect information game, there are many unknown variables. A player does not know his opponents’ cards and may not know their style of play — how aggressive they tend to be, for instance, or how often they bluff.

Unlike a chess bot, a poker bot does most of its work before the match, running millions of simulations before the first card is dealt. But even with the large amounts of memory available with today’s computers, storing — or even computing — information for every possible scenario would be implausible.

The best poker bots in the world include those from the University of Alberta Computer Poker Research Group, which is nearly 20 years old. Professor Michael Bowling, who has led the group since 2005, says the breakthrough came in 2003, when researchers decided to change their approach, shifting away from the methodology used to build chess bots.

In 2006, the inaugural Annual Computer Poker Competition created more interest in poker-playing computers and established a friendly rivalry between the University of Alberta and Professor Tuomas W. Sandholm’s poker research group at Carnegie Mellon University in Pittsburgh.

Today, Professor Sandholm said, poker bots “can rival good players, but not the best — yet.”

Many of the poker bots available on the Internet were built by programmers as a personal exercise or hobby. Some buyers think they can make money with the bots, but others use them in intellectual exercises, Mr. Jetter said. Buyers can program their bots to use different decision-making strategies in various circumstances, and then observe which outcomes are more successful when applied in real-world games.

“Using a poker bot is in fact a natural extension of the game of online poker,” said Mr. Jetter, who added that Shanky has sold 5,000 copies of its Holdem Bot software since it was introduced in early 2008. “Creating your own playing profile is a fun challenge that many players enjoy.”

That argument does not go over well at sites like PokerStars. Last year, after it was tipped off by Mr. Taylor, the company found 10 bots and returned more than $57,000 to players who had lost money to them.

The poker bots’ arrival may be just another sign of an emerging world where humans, knowingly or unknowingly, encounter robots on an everyday basis. People already talk with computers when they call customer service centers or drive their cars.

As for Mr. Taylor, his cleverness in spotting bots won him a job. He now works full time for PokerStars, where “he is helping to protect the integrity of our games,” Mr. Josem said.

And so the human wins — this time.



Quant Headhunter
It seems to me that if you're smart enough to build a seriously good Poker bot, you really ought to be doing algorithmic trading, which is both more legal and more profitable.
Seems like a Kasparov program a little modified though where 90% of the times bots win. In Kasparov though 100% of time the program wins.
It seems to me that if you're smart enough to build a seriously good Poker bot, you really ought to be doing algorithmic trading, which is both more legal and more profitable.

If you're smart enough to make a _winning_ bot. Note that "More than 90% are losing money."
I wouldn't want to have those odds algorithmically trading.
1: Speed of code execution is less important for the bot (poker is turn-based with ample time given for "thinking")
2: If the bot targets games where playing skill is weak, it doesnt have to be all that sophisticated in order to be seriously good.

That being said, I still agree with you.


Quant Headhunter
I didn't know that statistic, euroazn and I confess it surprises me, do you have a link ?

Why would someone go to the effort of building a bot that loses money ?

It gives me the mental image of a lone genius building a robot in his basement that has the delicacy of touch that can pick up an individual dollar bill from a stack and tear it into 1,317 identically sized pieces.
I didn't know that statistic, euroazn and I confess it surprises me, do you have a link ?

That statistic is right in the article above. Though it's probably a bit exaggerated to discourage people from using them (the source is pretty biased).


Quant Headhunter
That reminds me of when I was first learning AI, my tutor defined 'intelligent' as anything a computer could not do :)

A good bot would be hard to detect, and a brilliant bot even harder, (apart from winning a lot of course), so it may be that if the statistic is true, it actually means "90% of bots that are so crap that we can spot them, lose money".

I was once told by a very senior British law enforcement official that not one person they had ever prosecuted for computer fraud had a degree in the subject. That could mean of course that CompSci grads are inherently honest, upright citizens, or...
Nevertheless, I wouldn't be surprised if the majority of bots have poor odds. There are a lot of variables in poker to consider - and if you want to have better odds than the other players, you have to analyze their playing styles.
If we agree that it is possible to write a code which takes into account all possible resistive movements(again, like Kasparov in chase), then the program just looses 10% of time creating the impression that it is not that sophisticated willing to win all the time. It can loose if you are "smart enough" to resist the perfect code. That is the philosophy of creating such an algorithm I think.
It seems to me that if you're smart enough to build a seriously good Poker bot, you really ought to be doing algorithmic trading, which is both more legal and more profitable.

Doing algorithmic trading you are competing against Goldman Sachs & Co., their army PhDs, flash trades etc., while in poker you will compete with a bunch of young kids who don't even know basics of statistics.


Older and Wiser
I read the article and I'm really skeptical. I don't think there is a way to verify that you are really shutting down a bot. IMHO, the poker sites are closing accounts and people are not putting up a fight. Probably because, indeed, they are using a bot but that is extremely hard to prove.

I also don't believe that 90% of the bots are losing money. If that is the case, there is no way the poker sites will shut them down. The house will be making money very easily. I don't see the incentive.

Also, I know it was possible to get the history of the hands you play in this online poker sites. The history came in some sort of logs and you can analyze and probably, apply some data mining techniques. The bots could take advantage of this in order to form a strategy.
There's no way to put a fight with a poker site. They are not regulated and can do whatever they please. You can try to beg, prove something etc and if they feel merciful today they will let you continue. But I know several cases in which accounts were closed and all funds confiscated for very minor or none at all violation of rules.

Statistically it's impossible to prove that bot is playing. If certain account implements a very basic strategy and follows it all the time it doesn't mean that this is bot. However, contemporary bots are way more sophisticated than that. They use various distributions to "mix" their play, to vary time they take to make a decision etc.
I donno the rules of poker quite well but if I knew I would think at least how to simulate and construct such a bot winning 90% of time making the false impression that it can be won over and making the slots in varying time intervals. I know the constructs of Kasparov how it works, it simulates all the possible next movements of opponent and takes the necessary path. When one of the next possible movements actually occurs then it simulates all the next possible movements and so on.


Older and Wiser
One way to detect the presence of a bot is by sending a message to the player. All these poker sites have a way for the players to communicate with each other by means of IM of some sort. Posing as an administrator of the site and asking a question regarding the state of the game might lead to detect a bot. This is just an idea but it's trivial and relatively easy to implement.

I know the bot writer will come up with ways to go around it but this could be a good starting point.