1. Home>
  2. Poker News>
  3. Alberta’s DeepStack Crushing Poker at 49 BB per 100
  • Alberta’s DeepStack Crushing Poker at 49 BB per 100

    Friday, March 3rd, 2017 by Jeremy Olsen

It hasn’t been long since Carnegie Mellon’s poker bot, Liberatus, crushed four poker pros to the tune of $1.76 million. And now, we get word that the Unversity of Alberta’s less-heralded DeepStack is winning 49 big blinds per 100.

DeepStack lead author Michael Bowling discussed the dominance that his AI is showing with Inverse.

”We are winning by 49 per 100, that’s like saying whatever the players were doing was not that much more effective than if they just folded every hand,” said Bowling. “To put it into perspective, a pro player is trying to win by a rate of about five big blinds per 100. If they can make that rate than they are good enough to make a profit and a living playing poker. And we were beating that by nearly ten times.”

So what makes DeepStack another dominant AI in poker?

According to Bowling, the bot continues improving through recursive learning, or the back-and-forth exchange that involves determining how much information your opponent thinks you know, and vice versa.

“If my opponent thinks I have really good cards and thinks I know about his cards, then he is going to fold,” Bowling explained. “This is recursive reasoning, it’s how to think through ‘what does everybody actually know’ and how to make decisions accounting for all of that.”

DeepStack can actually bluff other players and strategize a few decisions ahead. The latter is a change from previous AIs, which were programmed to see to the end of the game – not exactly the best strategy when facing a human who adjusts.

“Ideally, the program would figure out if it’s going to win or lose and find a path through that situation to win,” said Bowling. “But, that situation base is huge and there’s no way it could look all the way to the end of the game from the very beginning, it’s just too far away. So, DeepStack only looks a few decisions ahead and asks itself if a guess might be worth it and I liken that guess to intuition.”

Just like Liberatus, Bowling says that DeepStack is created for greater purposes than just playing poker. These include helping people make better financial decisions, reducing the chance for terrorism by monitoring flight schedules, and helping public transportation.

You can read the entire piece here at Inverse.




About Us | Contact Us | Disclaimer | Privacy Policy | Site Map

If you are interested in learning more about online poker, try searching on Yahoo, the Open Directory Project, or Bing.