Written by :
Published on :
- Artificial Intelligence named Libratus to take on human poker pros next week
- Imperfect information games like poker could prove more of an obstacle for AIs
- This AI looks to strike the perfect balance of risk and reward
- The AI will often go against convention wisdom discussed in poker strategy books
Next week, an Artificial Intelligence developed by Carnegie Mellon University named Libratus is set to take on real human poker pros. Who will prevail?
Poker is an imperfect-information game, which makes it far more challenging for artificial intelligence to master, writes Ben Popper of TheVerge.com.
“In a complete information game you can solve a subtree of the game tree,” says Professor Tuomas Sandholm, who built the Libratus system with PhD student Noam Brown. AI trying to win a game of chess or Go can work through how a sequence of moves will play out. “With incomplete-information games, it’s not like that at all. You can’t know what cards the other player has been dealt,” he explains. “That means you don’t know exactly what subgame you’re in. Also, you don’t know which cards chance will produce next from the deck.”
CMU’s AI focuses on information sets, a grouping of possible states that take into account the known and unknown variables, Popper notes.
Rather than merely strategize many moves in advance, as AI might do when playing chess or Go, the system built by CMU is looking to achieve the perfect balance of risk and reward, a state of play defined by the Nash Equilibrium.
“In these two-player zero sum games, if the other player doesn’t play a Nash equilibrium strategy, that means they are playing worse, and we are making more money,” explains Sandholm. “In such games, playing Nash equilibrium is safe. It has the flavor where it plays rationally and is not exploitable anywhere.”
Poker pro Jason Les returns to face Libratus after going up against a prior CMU AI system.
“I always tell people the one word I can use to describe the experience: a grind,” Les said. “The first few days we ended up playing til midnight, and when we were done we went back to the hotel and studied for a few hours before going to sleep. Then we would wake up at 9AM and do it all over again,”
Popper suggests that the Carnegie Mellon AI will often go against convention wisdom discussed in popular poker books.
Popper writes:
For example in the first move in a hand of poker, limping means you just call the opponent, you put in the minimum amount of money to continue the hand. All the poker books say that is a terrible move, but
CMU’s poker bots limp somewhere between 7–16 percent of the time.
“That really contradicts the folk wisdom on how to play this game,” says Sandholm. “The algorithms figure it out just from the rules of the game, we don’t give them any historical data about how humans play. They play like Martians, they figure out their own strategy.”
The AI vs. Poker Pro matches are scheduled for January 11th at the River Casino in Pittsburgh, PA, home of Carnegie Mellon. The pros to go up against Libratus will be — Jason Les, Dong Kim, Daniel McAulay, and Jimmy Chou. They will collectively play 120,000 hands over the course of the 20-day tournament with a $200,000 prize purse. Live streaming will be available via Twitch.
- Ace King, Gambling911.com
