Congratulations Carnegie Mellon University on becoming the first to build a supercomputer to beat 4 pros in poker! Libratus is an artificial intelligence (AI) program for playing Heads-Up, No-Limit Texas Hold’em. It was developed at Carnegie Mellon University’s School of Computer Science by Prof. Tuomas Sandholm and Ph.D. Student Noam Brown. Rivers Poker Room. It’s non-stop action in the Rivers Casino Poker Room. Stop by and let us know how we’re doing or what you may be interested in having us add to our room. Why play anywhere else? The room is 8,457 square feet that holds 30 tables. Limit and No Limit Texas Hold’Em/Omaha Hi-Low and Pot Limit Omaha are among many games we offer.
Monday was another losing day for the human team, but the bleeding was finally stopped.
After the completion of the 120,000 hands against Carnegie Mellon University’s poker machine Libratus, the poker pro team was down 1,776,250 chips. The chips have no cash value, but the poker pros are splitting a $200,000 purse for a grueling battle against the best poker playing robot ever developed.
“We’re not paying,” Jason Les, one of the poker pros to play Libratus, joked at a press conference Tuesday. “I showed up thinking there was a good chance we would lose, but I thought it would be a lot closer. It’s truly a monumental day in AI.”
Les lost 880,097 to the bot, which was worst on the team. Jimmy Chou was in the hole 522,857, and Daniel McAulay lost by 277,657. Dong Kim, who was in the black for a good portion of the 20-day contest, finished down just 85,649 chips.
“We really got a beat-down,” McAulay said.
The 1.7 million chips was about 17,000 big blinds, or about 14 big blinds per 100 hands. That was nearly 90 buy-ins, as every hand of the contest began with the human player and the machine sitting with 20,000 chips (200 big blinds).
The event, dubbed “Brains vs. AI”, was held at Rivers Casino in Pittsburgh.
Libratus was just the latest poker bot from CMU computer scientist Tuomas Sandholm. Libratus was designed by Sandholm and his PhD. student Noam Brown.
“Heads-up no-limit hold’em had been elusive,” Sandholm said of the challenges behind beating top human players in the game. “This is a landmark in AI game play.”
“The poker pros are real sportsmen,” Sandholm said at the press conference. After every night of play, the team met to discuss strategies and try to find leaks in Libratus’ game. Unfortunately, they weren’t able to find much.
Libratus was also fine-tuned after sessions, which led to the human team feeling like the bot was getting better every day. “It learns from us and the weakness disappears the next day,” Chou said during the contest.
Each night after a session, the Pittsburgh Supercomputing Center’s Bridges computer performed computations to sharpen Libratus’ strategy. On Monday, Brown posted an academic paper on the complex game theory behind Libratus.
An earlier version of Libratus called Claudico was defeated by a different group of poker pros in the spring of 2015. However, CMU called the 7,300 big blinds a “statistical tie.”
Sandholm called this year’s result “highly statistically significant.”
“Since the earliest days of AI research, beating top human players has been a powerful measure of progress in the field,” Sandholm said. “That was achieved with chess in 1997, with Jeopardy! in 2009 and with the board game Go just last year. Poker poses a far more difficult challenge than these games, as it requires a machine to make extremely complicated decisions based on incomplete information while contending with bluffs, slow play and other ploys.”
While Libratus was able to win in heads-up no-limit hold’em with 200 big blind stacks, the bot wouldn’t be able to handle additional players at the table, and the match could have gone very differently if the stacks were much deeper than 200 big blinds.
Libratus used a very balanced and powerful (literally what Libratus means in Latin) river over-bet strategy with both bluffs and value bets that kept the humans generally confused.
Because Libratus was designed specifically for the Brains vs. AI battle, and the fact that it cost millions of dollars to develop and run, online poker players shouldn’t fear that AI like Libratus will threaten the integrity of internet games anytime soon. Online poker companies are also highly sophisticated at detecting robot players. It’s also worth mentioning that Libratus would sometimes go deep into the tank on later streets, something that wouldn’t be possible at a real internet poker table.
Claudico is an artificial intelligence computer program designed to play no limit Texas hold 'em heads-up.
History[edit]
Claudico was designed by Carnegie Mellon professor Tuomas Sandholm and his graduate students. The name means 'I limp' in Latin, a reference to limping into a hand without raising—a strategy the bot employs often.[1] Rather than have a professional poker player attempt to explain his strategy to the programming team, Sandholm had the computer attempt to devise the best strategy on its own. The task was so complicated that it required a Pittsburgh Supercomputing Center Blacklight supercomputer with 16 terabytes of RAM to complete.[2]
In explaining his motivation for designing the bot, Sandholm said, 'Poker is now a benchmark for artificial intelligence research, just as chess once was. It's a game of exceeding complexity that requires a machine to make decisions based on incomplete and often misleading information, thanks to bluffing, slow play and other decoys'.[3]
Originally called Tartanian, a version of the program won a July 2014 tournament against other computer programs.[3]
The improved successor of Claudico is called Libratus. Like Claudico, Libratus is designed to compete against top human players.
2015 match against four human players[edit]
From April 24 to May 8, 2015, Claudico participated in an event at Rivers Casino in Pittsburgh, Pennsylvania. The bot faced each of four top human opponents—Dong Kim, Jason Les, Bjorn Li, and Doug Polk—in a series of heads-up matches.[3] At the time, Polk was the world's number-one ranked heads-up player.[1]
Each day featured two 750-hand matches over eight hours (plus breaks) against each of the humans, for a total of 20,000 hands per player over the course of 13 days (with one rest day in the middle).[1][2] For each 750-hand set, the same hands were dealt to one human taking on Claudico on the main casino floor and another battling the computer in an isolation room, with the hole cards reversed.[4] This was done to ensure that card luck was not a factor in the outcome. The 80,000-hand sample represented the largest-ever human–computer data set. Claudico was able to adjust to its opponent's strategy as the matches progressed, just as the humans could.[2] The match winner was determined by the overall chip count after 80,000 hands; although individual results were kept for the four pros, they were competing as a single team. If the final chip count had been too close for the difference to be statistically meaningful, the match would be declared a draw.[4]
The tournament carried a $100,000 prize pool, funded by Rivers Casino and Microsoft. The casino set up stands and video screens for the public to watch the action live.[1] Additionally, the matches were broadcast online via Twitch.[3] Highlights from the match will air throughout 2015 on CBS Sports Network's weekly show Poker Night in America.[5]
Entering the event, Sandholm estimated that Claudico had a 50/50 chance to win.[3] Polk, however, was confident the humans had the edge.[2] He acknowledged that computers would likely surpass human play eventually, but said, 'I hope we can make them go a few more rounds after this before they do, like Kasparov did'.[1] He said his strategy would 'change more so than when playing against human players ... I think there will be less hand reading so to speak, and [fewer] mind games'.[3]
The blinds were 50 and 100 chips for every hand, and both the human's and computer's chip stack were reset to 20,000 at the beginning of each hand. Halfway through the match, the human team was ahead 458,000 chips versus Claudico.[6] The humans went on to increase their lead, winning the match by 732,713 chips. Polk finished up 213,000, Li won 529,000, Kim beat Claudico by 70,000, and Les finished down 80,000. A total of 170 million chips were bet over the 80,000 hands. Polk said Claudico had played well in spots, but also made some bad plays. Overall, it played very differently than humans. 'Where a human might place a bet worth half or three-quarters of the pot, Claudico would sometimes bet a miserly 10 percent or an over-the-top 1,000 percent', he explained. 'Betting $19,000 to win a $700 pot just isn't something that a person would do'.[5]
See also[edit]
References[edit]
Rivers Casino Poker Blog
- ^ abcdeSean D. Hamill (April 24, 2015). 'Who's got the upper hand? Poker computer program pits man against machine'. Pittsburgh Post-Gazette. Retrieved April 26, 2015.
- ^ abcdTim Fiorvanti (April 24, 2015). 'Brains vs. AI: Poker's Top Heads-Up Pros Take on Computer Program in Two Week Challenge'. Bluff. Archived from the original on May 6, 2015. Retrieved April 26, 2015.
- ^ abcdefMarilyn Malara (April 25, 2015). 'Brains vs. AI: Computer faces poker pros in no-limit Texas Hold'em'. UPI. Retrieved April 26, 2015.
- ^ ab'Brains Vs. Artificial Intelligence'. Rivers Casino. Retrieved April 26, 2015.
- ^ abJason Glatzer (May 11, 2015). 'Man Proves Greater Than Machine: Players Win $732,713 Against Bot 'Claudico''. Poker News.
- ^Jason Glatzer (May 4, 2015). 'Man vs. Machine: Pros Ahead of 'Claudico' Over $450,000 After Seven Days'. Poker News.
External links[edit]
Rivers Casino Poker Tournaments
- Brains Vs. Artificial Intelligence official website at CMU
- Brains Vs. Artificial Intelligence official website at Rivers Casino