New AI just ‘decisively’ beat pro poker players in 7 day tourney and demonstrates mastery of imperfect information games

New AI just ‘decisively’ beat pro poker players in 7 day tourney and demonstrates mastery of imperfect information games

Developed by Carnegie Mellon University, a new AI called Libratus won the “Brains Vs. Artificial Intelligence” tournament against four poker pros by $1,766,250 in chips over 120,000 hands (games). Researchers can now say that the victory margin was large enough to count as a statistically significant win, meaning that they could be at least 99.7 percent sure that the AI victory was not due to chance.

The four human poker pros who participated in the recent tournament spent many extra hours each day on trying to puzzle out Libratus. They teamed up at the start of the tournament with a collective plan of each trying different ranges of bet sizes to probe for weaknesses in the Libratus AI’s strategy that they could exploit. During each night of the tournament, they gathered together back in their hotel rooms to analyze the day’s worth of plays and talk strategy.

The AI took a lead that was never lost. It see-sawed close to even mid-week and even shrunk to $50,000 on the 6th day. But on the 7th day ‘the wheels came off’. By the end, Jimmy Chou, became convinced that Libratus had tailored its strategy to each individual player. Dong Kim, who performed the best among the four by only losing $85,649 in chips to Libratus, believed that the humans were playing slightly different versions of the AI each day.

After Kim finished playing on the final day, he helped answer some questions for online viewers watching the poker tournament through the live-streaming service Twitch. He congratulated the Carnegie Mellon researchers on a “decisive victory.” But when asked about what went well for the poker pros, he hesitated: “I think what went well was… shit. It’s hard to say. We took such a beating.”

The victory demonstrates the AI has likely surpassed the best humans at doing strategic reasoning in “imperfect information” games such as poker. But more than that, Libratus algorithms can take the “rules” of any imperfect-information game or scenario and then come up with its own strategy. For example, the Carnegie Mellon team hopes its AI could design drugs to counter viruses that evolve resistance to certain treatments, or perform automated business negotiations. It could also power applications in cybersecurity, military robotic systems or finance.

http://spectrum.ieee.org/automaton/robotics/artificial-intelligence/ai-learns-from-mistakes-to-defeat-human-poker-players

 

Leave a Reply

Your email address will not be published. Required fields are marked *