It’s starting to look like Carnegie Mellon University has a gambling problem – can’t stay away from the poker table. This morning CMU reports its latest Poker-playing AI software, Libratus, is winning against four of the world’s best professional poker players in a 20-day, 120,000 hand tournament – Brains vs. AI – at Rivers Casino in Pittsburgh. Maybe it’s a new way to fund graduate programs. (Just Kidding!)
One of the pros, Jimmy Chou, said he and his colleagues initially underestimated Libratus, but have come to regard it as one tough player, “The bot gets better and better every day. It’s like a tougher version of us.” Chou and three other leading players – Dong Kim, Jason Les and Daniel McAulay – specialize in this two-player, unlimited bid form of Texas Hold’em and are considered among the world’s top players of the game.
According the CMU report, while the pros are fighting for humanity’s pride – and shares of a $200,000 prize purse – Carnegie Mellon researchers are hoping their computer program will establish a new benchmark for artificial intelligence by besting some of the world’s most talented players.
Libratus was developed by Tuomas Sandholm, professor of computer science, and his student, Noam Brown. “Libratus is being used in this contest to play poker, an imperfect information game that requires the AI to bluff and correctly interpret misleading information to win. Ultimately programs like Libratus also could be used to negotiate business deals, set military strategy, or plan a course of medical treatment – all cases that involve complicated decisions based on imperfect information,” according to the CMU report.
CMU, of course, has been sharpening its AI poker skills for quite some time. Back in the fall of 2016, CMU’s software Baby Tartanian8, also created by Sandholm and Brown, won both the bankroll instant run-off category and the elimination competition of another computer poker tournament (see HPCwire article, CMU’s Baby Tartanian8 Pokerbot Sweeps Annual Competition).
Back then Sandholm said, “Our ‘baby’ version of Tartanian8 was scaled down to fit within the competition’s 200 gigabyte data storage limit. It also could not do sophisticated, real-time deliberation because of the competition’s processing limit. The original Tartanian8 strategy was computed in late fall by myself and Noam on the Comet supercomputer at the San Diego Supercomputer Center (SDSC).”
In the spring of 2015 CMU’s Claudico software fared well in competition (See HPCwire article, CMU’s Claudico Goes All-In Against World-Class Poker Pros). In that first Brains Vs. AI contest in 2015, four leading pros amassed more chips than the AI, called Claudico. But in the latest contest, Libratus had amassed a lead of $459,154 in chips in the 49,240 hands played by the end of Day Nine.
Here’s a link to the CMU article: http://www.cs.cmu.edu/news/cmu-ai-tough-poker-player