Please create an account to participate in the Slashdot moderation system


Forgot your password?
AI Math

CMU Researchers Reveal How Their AI Beat The World's Top Poker Players ( 36

2017 began with an AI named "Libratus" defeating four of the world's best poker players. Now the AI's creators reveal how exactly they did it. An anonymous reader quotes the Pittsburgh Tribune-Review: First, the AI made the game easier to understand. There are 10**161 potential outcomes in the game of poker -- that's a one followed by 161 zeros, potential outcomes in a game of poker. Libratus grouped similar hands, like a King-high flush and a Queen-high flush, and similar bet sizes to cut down that number. Libratus then created a detailed strategy for how it would play the early rounds of the game and a less-refined strategy for the final rounds. As the game nears the end, Libratus refined the second strategy based on how the game had gone.

A third strategy was at work as well. In real-time, Libratus created another model based on how its play stacked up against the play of the humans. If the humans did something unexpected to Libratus, the AI accounted for it and built it into the strategy. Instead of trying to exploit weaknesses in the play of the human, Libratus focused on improving its play.

The AI was created by a computer science professor at Carnegie Mellon University and his Ph.D. student, who argue in a new paper that "The techniques that we developed are largely domain independent and can thus be applied to other strategic imperfect-information interactions, including non-recreational applications."

"Due to the ubiquity of hidden information in real-world strategic interactions, we believe the paradigm introduced in Libratus will be critical to the future growth and widespread application of AI."
This discussion has been archived. No new comments can be posted.

CMU Researchers Reveal How Their AI Beat The World's Top Poker Players

Comments Filter:
    • by sfcat ( 872532 )
      That was one of the worst ML "papers" I've ever seen. I'm not sure who this guy is, but the paper's didn't use the standard ML jargon for any of the techniques they used. If CMU wasn't attached (disclaimer, I have a CS degree from CMU), I might claim that this is probably a Mechanical Turk. The system seems to use a mix of game theory, alpha-beta pruning and RL techniques (specifically Actor-Critic) but none of the "correct" descriptions or references to those things are present in the article. I guess
  • by Mal-2 ( 675116 ) on Sunday December 24, 2017 @08:19PM (#55802235) Homepage Journal

    It was one thing when bots could beat up on donkeys, but when even the best human players can't win it means only bots will be left standing. That doesn't mean humans are totally out of the loop, someone still has to be standing by to talk to the admin when questioned about their human status -- for now. That too will probably fall before long.

    The micro-stakes tables will probably remain largely human because there's very little to lose (or gain) down there, but for high-stakes games this signals a rapidly approaching end.

    • by mentil ( 1748130 )

      Anyone who plays high-stakes online poker can afford to physically go somewhere and do it in person. Of course, then people will have a bone-conduction speaker hidden somewhere on their person, receiving instructions from an AI. Until the hosts start doing bug sweeps.

  • by nospam007 ( 722110 ) * on Sunday December 24, 2017 @08:21PM (#55802239)

    It's way harder if you know you may end sleeping in your car for a couple of years if you lose.

    • No it isn't, it's exactly as hard. The second you start having thoughts about losing you're dead money. That's kind of the whole point of poker.

  • It is kind of silly. Reality is the least capable computer can beat the smartest person all of the time, as long as it is not a race. The computer can keep going and going and going, long after the person gives up [].

  • by 140Mandak262Jamuna ( 970587 ) on Sunday December 24, 2017 @08:44PM (#55802307) Journal
    By counting cards. The bouncers will have it thrown out in a minute.
    • In poker the players will just kick you ass in the parking lot if you cheat them

    • Counting cards is in blackjack. Not enough cards are seen in Texas Hold'em to make a difference. The deck is reshuffled every hand, anyway, negating the advantages of card counting. Sad to see basic ignorance like this modded up.
  • So? (Score:4, Insightful)

    by fluffernutter ( 1411889 ) on Sunday December 24, 2017 @09:17PM (#55802417)
    It kind of defeats the point of AI if you preload it with all kinds of statistics a human wouldn't have access to while playing a game. The point of AI is to make a computer think and learn like a human, not to prove that a computer can beat a human. We already know computers are better at calculations than humans.
    • by hey! ( 33014 )

      The point of AI is to make a computer think and learn like a human, not to prove that a computer can beat a human.

      Well, that's one possible point of AI. Other possible goals would be to generate better results, or good-enough results but much more cheaply. Yes, there have always been people who have hoped to shed light on human intelligence by creating machine intelligence, but by in large they haven't had as much to show for their efforts as people trying to improve on people in some way (performance or cost).

      • by Kjella ( 173770 )

        I feel it's been more the opposite, people claiming machines can never do this or that until they have human intelligence. And since we don't really know what that is or how to build it, we can't have it. And then we have AI - but since so many people seem to get their panties in a bunch about that term I'll just say adaptive algorithms - that do it better anyway. And despite it's encroaching on more and more human jobs we're clinging to our own unique abilities as important.

        If I'd like to eat a hamburger,

        • So what is left for humans are the areas of the economy that very few people are willing to pay for. It's already fairly common knowledge that a general arts degree ain't going to cut it. Nothing about AI is going to make that a better career; if anything, since there will be greater concentration of wealth, less people will be able to afford the arts and the rise in ticket prices won't cut it. But I digress.
          Automated driving needs real AI to be truly as safe is being marketed. It's that simple. Sur
    • by mentil ( 1748130 )

      You're kidding, right? Read any 'how to win at blackjack/poker/gambling' book and, right after the rules, it will give all of the precise odds for all of the means of winning. Amateur gamblers are expected to memorize ALL of these odds, this is Gambling 101. IIRC, it's allowed to bring a 'cheat sheet' of all of these odds into a casino, as well. In this case, humans know a bunch of statistical information regarding the game. That said, this AI did improve its strategy over time, which could be called 'intel

      • So if the stats are so easy to remember, why don't humans do as good as the computer? Because it is harder for a human to use them effectively than you are making it sound. But he ability for a computer to use them effectively is no surprise.
    • It kind of defeats the point of AI if you preload it with all kinds of statistics a human wouldn't have access to while playing a game. The point of AI is to make a computer think and learn like a human, not to prove that a computer can beat a human. We already know computers are better at calculations than humans.

      In the context you are talking about I always though AI was the wrong term also since all it i really do is many more complex computations father than a human can but not really coining up with any cognitive thought. While that is useful as an adjunct to human problem solving it really isn't intelligence. Years ago when I was in high school I attendee series of classes taught by some researchers on pattern recognition; which is really what this is except with a lot more computational power.

  • by Blue23 ( 197186 ) on Tuesday December 26, 2017 @11:40AM (#55809105) Homepage

    I followed this as it was happening. This is NOT about bots being able to beat human players. It's about bots being able to beat human players in the simplest possible space that doesn't mimic 99% of actual poker play.

    It was only heads-up with 1 human a time, not vs. a table. After every round the money was reset so it never had to play from low amount of chips, or have to try to bully with it's chip advantage. The amount of chips vs. the big blind was a very large stack in the first place even before it reset every hand, so the blinds were statistically little more than noise in the amount that was going back and forth.

    Don't get me wrong, this is really interesting and great strides. But this is far from a bot being able to play at a full table and having to deal with a few bad hands taking it out of the place where it's betting is suited for. (If you have less of a stack, you have less of an upside so draw hands aren't worth as much.) Or to have someone with a larger stack push it beyond it's acceptable betting and make it fold because it can.

This login session: $13.76, but for you $11.88.