Poker Bots Getting Better
But the majority is still pretty bad…
Achieving wide coverage over the weekend was an article from the New York Times on internet poker bots which examined the current state of play in artificial intelligence, and the position of major online poker sites regarding use of the software programs.
The article carried anecdotal reports of experienced players who can often identify bot users just from their playing styles, but it points out that bot technology has been steadily improving, especially in formally weak areas like bluffing.
The biggest online poker providers, Pokerstars and Full Tilt, both have sophisticated bot-detection software and take a hard line against the use of bot programs against their human players. Most other sites have anti-bot provisions in the T&Cs which lead to instant dismissal and disqualification of winnings when a bot is detected.
Pokerstars security manager Michael Josem told the newspaper: “Pokerstars is continuing to invest substantial resources to combat bots. When a player is identified as a bot, Pokerstars removes them from our games as soon as possible.” He added that the offending players had their winnings confiscated, and where appropriate the company provides compensation to players.
Despite bans on internet poker sites, bot sales apparently are good business. Shanky Technologies, which sells licenses for the Holdem Poker Bot for $129 per year, spoke to the newspaper, co-founder Brian Jetter revealing that over 400 of his customers had been banned from Full Tilt in a recent anti-bot drive, with over $50 000 in winnings confiscated from players using the bot.
Jetter feels that sites like Full Tilt are foregoing revenues of around $70 000 a month by taking an anti-bot stand against his product
“They really must have wanted us gone,” Jetter said. “We don’t think the other poker rooms we support will make a similar financial decision.”
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.
He said that 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,” claimed Jetter, adding 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,” he claimed.
Although they are improving, the general run of poker bots are not stellar players, the New York Times notes.
Supporting this claim, it quotes Darse Billings, a consultant to Pokerstars and Full Tilt and the former chief of data analytics at Full Tilt, who said: “The large majority of bots are very bad. More than 90 percent are losing money.”
Billings pointed out that it is easier to build a chess bot than a poker equivalent. "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," he said.
"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 New York Times report identifies some of the best poker bots in the world as those developed for research purposes at the University of Alberta Computer Poker Research Group, now 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, the newspaper reveals.
Today, Professor Sandholm said, poker bots “can rival good players, but not the best…. yet.”
Although bot users are penalised when caught, the poker site itself can be financially prejudiced by their activities; the New York Times piece uses a recent incident at Pokerstars as an example, where 10 bots were uncovered but the site paid some $57 000 in compensation to innocent players impacted by the bot users.
