Poker bots are getting better

Not long ago, but merely 2 years we were introduced to a poker bot named Cepheus, which was developed by the Computer Poker Research Group (CPRG) at the University of Alberta. The team, which was led by Dr. Michael Bowling and included Neil Burch, Michael Johanson, and Oskari Tammelin, published a paper “Heads-up limit hold’em poker is solved” in Science, where you can read all the details about it.

“While Cepheus does not play perfectly, it is so close to perfect that even after playing an entire lifetime of poker against it — over 60 million hands — it is impossible to tell the difference. It is essentially perfect.”

“Cepheus accomplished this goal with no human expert help, only being given the rules of the game. It was trained against itself, playing the equivalent of more than a billion, billion hands of poker. With each hand it improved its play, refining itself closer and closer to the perfect solution. The program was trained for two months using more than four thousand CPUs each considering over six billion hands every second! This is more poker than has been played by the entire human race.”

You can also play Cepheus on their website and examine his strategy in detail.

But can poker bots defeat pro players in NL Texas Hold’em?

Well I can quite understand solving pot limit texas hold’em head’s-up, as the number of choices is considerably limited, but recently we are hearing about new poker bots being trained in no limit texas hold’em.

A team of researchers recently published a paper called “DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker”, where you can read:

“There has been some AI success in heads-up limit
Texas hold’em, the smallest variant of poker played by humans. However, heads-up limit Texas hold’em has
fewer than 10^14 decision points. By comparison, computers have exceeded expert human per-
formance in go a perfect information game with approximately 10^170 decision points. The comparable variant of poker is heads-up no-limit Texas hold’em (HUNL). In HUNL, the two players can bet any number of chips, resulting in over 10^160 decision points”
“We evaluated DeepStack by playing it against a pool of professional poker players recruited

by the International Federation of Poker(…)

In total 44,852 games were played by the thirty-three players with 11 players completing
the requested 3,000 games. Over all games played, DeepStack won 492 mbb/g(…)
In the poker community, it is common to use big blinds per one hundred games (bb/100) to measure win rates, where 10 mbb/g equals 1 bb/100.”

Poker bot named Libratus

Great job, DeepStack team! I guess we’ll have to wait and see how DeepStack does after playing more hands, but so far these results are looking great.

What’s interesting, at the same time there’s another bot being tested playing against proffesional poker players. Its name is Libratus and it was developed in Carnegie Mellon University.

“Libratus developed its knowledge of the game and its strategy by analyzing the rules of the game, not by trying to copy the play of humans. The AI calculated its poker strategy using about 15 million core hours of computation on the Pittsburgh Supercomputing Center’s Bridges computer. Ralph Roskies, scientific director of the PSC, said this use of Bridges already has generated 2 1/2 petabytes of data.”

Libratus is now being tested in a competition called “Brains Vs. Artificial Intelligence: Upping the Ante”, where it will play 120,000 hands against 4 pros: Jason Les, Dong Kim, Daniel McAulay and Jimmy Chou.

You can read more about it and even watch the challange live on twitch on this website.

So far after playing 23,340 hands, the poker bot is up $159,288!

So artificial intelligence or humans?

The results are looking really promissing so lets say it is possible for poker bots to perfect heads-up no limit texas hold’em, just like they did limit holdem.

What’s next?

Can AI ever play a better game than some of the best players in the world on 6-max tables or full ring tables?

Well I guess we’ll just have to wait and see…