{"id":826,"date":"2018-01-04T12:54:43","date_gmt":"2018-01-04T12:54:43","guid":{"rendered":"https:\/\/wordpress.nkisiland.com\/?p=826"},"modified":"2018-01-04T12:57:11","modified_gmt":"2018-01-04T12:57:11","slug":"cmu-artificial-intelligence-is-tough-poker-player-libratus-builds-substantial-lead-in-brains-vs-ai-competition","status":"publish","type":"post","link":"https:\/\/wordpress.nkisiland.com\/?p=826","title":{"rendered":"CMU Artificial Intelligence Is Tough Poker Player. Libratus builds substantial lead in Brains vs. AI competition"},"content":{"rendered":"

As the \u201cBrains Vs. Artificial Intelligence: Upping the Ante\u201d<\/span> poker competition nears its halfway point, Carnegie Mellon University\u2019s AI program, called Libratus, is opening a lead over its human opponents \u2014 four of the world\u2019s best professional poker players. Libratus had amassed a lead of $459,154 in chips in the 49,240 hands played by the end of Day Nine. (from cmu.edu)<\/strong><\/p>\n

One of the pros, Jimmy Chou, said he and his colleagues initially underestimated Libratus, but have come to regard it as one tough player. \u201cThe bot gets better and better every day,\u201d Chou said. \u201cIt\u2019s like a tougher version of us.\u201d<\/p>\n

\n
\n
\n
\n

Brains Vs. AI, which began Jan. 11 2017 at Rivers Casino in Pittsburgh, pits Chou and three other leading players \u2014 Dong Kim, Jason Les and Daniel McAulay \u2014 against Libratus in a 20-day contest in which they will play 120,000 hands of Heads-Up, No-Limit Texas Hold\u2019em poker. All four pros specialize in this two-player, unlimited bid form of Texas Hold\u2019em and are considered among the world\u2019s top players of the game.<\/p>\n

While the pros are fighting for humanity\u2019s pride \u2014 and shares of a $200,000 prize purse \u2014 Carnegie Mellon researchers are hoping their computer program will establish a new benchmark for artificial intelligence by besting some of the world\u2019s most talented players.<\/p>\n

Libratus was developed by Tuomas Sandholm<\/span>, professor of computer science, and his Ph.D. student, Noam Brown. Li<\/span>bratus 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 \u2014 all cases that involve complicated decisions based on imperfect information.<\/p>\n

In the first Brains Vs. AI contest in 2015, four leading pros amassed more chips than the AI, called Claudico. But Sandholm said he\u2019s feeling good about Libratus\u2019 chances as the competition proceeds. \u201cThe algorithms are performing great. They\u2019re better at solving strategy ahead of time, better at driving strategy during play and better at improving strategy on the fly,\u201d Sandholm said.<\/p>\n

Chou said he and the other pros have shared notes and tips each day, looking for weaknesses they can each exploit.<\/p>\n

\u201cThe first couple of days, we had high hopes,\u201d Chou said. \u201cBut every time we find a weakness, it learns from us and the weakness disappears the next day.\u201d<\/p>\n

The change from day to day is not unexpected, Sandholm said. Each night after poker play ends, the Pittsburgh Supercomputing Center<\/span>\u2019s Bridges computer performs computations to sharpen the AI\u2019s strategy. During the day\u2019s game play, Bridges is used to compute end-game strategies for each hand.<\/p>\n

\u201cThe people at the Pittsburgh Supercomputing Center have done a great job,\u201d Sandholm said, noting the staff has moved workloads around to enable the computer to be used in the competition. Since the beginning of the contest, the center has increased the number of Bridges\u2019 computer nodes assigned to the poker tournament.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"

As the \u201cBrains Vs. Artificial Intelligence: Upping the Ante\u201d poker competition nears its halfway point, Carnegie Mellon University\u2019s AI program, called Libratus, is opening a lead over its human opponents \u2014 four of the world\u2019s best professional poker players. Libratus … Continue reading →<\/span><\/a><\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[1],"tags":[],"_links":{"self":[{"href":"https:\/\/wordpress.nkisiland.com\/index.php?rest_route=\/wp\/v2\/posts\/826"}],"collection":[{"href":"https:\/\/wordpress.nkisiland.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/wordpress.nkisiland.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/wordpress.nkisiland.com\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/wordpress.nkisiland.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=826"}],"version-history":[{"count":4,"href":"https:\/\/wordpress.nkisiland.com\/index.php?rest_route=\/wp\/v2\/posts\/826\/revisions"}],"predecessor-version":[{"id":830,"href":"https:\/\/wordpress.nkisiland.com\/index.php?rest_route=\/wp\/v2\/posts\/826\/revisions\/830"}],"wp:attachment":[{"href":"https:\/\/wordpress.nkisiland.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=826"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/wordpress.nkisiland.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=826"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/wordpress.nkisiland.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=826"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}