Poker has been a challenging problem in AI and game theory for decades. As a game of imperfect information, it involves obstacles not present in games like chess and Go and requires totally different techniques. No program had been able to beat top players in large poker games. . .until now. In January 2017, an AI, Libratus, beat a team of four top specialist pros in heads-up no-limit Texas hold’em, which has 10^161 decision points. Libratus is powered by new algorithms in each of its three modules: computing approximate Nash equilibrium strategies before the event, endgame solving during play, and fixing its own strategy to play even closer to equilibrium based on what holes the opponents have been able to exploit.
Tuomas Sandholm offers an overview of Libratus and explains how Strategic Machine is applying the domain-independent algorithms behind it to a variety of imperfect-information games, such as business strategy, negotiation, strategic pricing, product portfolio planning, finance, cybersecurity, military applications, political campaigns, auctions, and steering biological adaptation and evolution for medical treatment planning.
(This is joint work with Tuomas’s PhD student Noam Brown.)
Tuomas Sandholm is professor in the Computer Science Department at Carnegie Mellon University, with affiliate professor appointments in the Machine Learning Department, the PhD program in algorithms, combinatorics, and optimization (ACO), and the CMU-Pitt joint PhD program in computational biology. He is the founder and director of the Electronic Marketplaces Laboratory; founder and CEO of Optimized Markets, Inc., which is bringing a new expressive optimization-powered paradigm to advertising campaign sales and scheduling in TV (linear and digital), streaming, internet display, mobile, game, radio, and cross-media advertising; and the founder and CEO of Strategic Machine, Inc., which provides solutions for strategic reasoning under imperfect information. Previously, Tuomas was founder, chairman, and CTO and chief scientist of CombineNet, Inc. His algorithms also run the UNOS kidney exchange, which includes 66% of the transplant centers in the US. He has served as market design consultant or board member for a number of companies, including Baidu, Yahoo, Google, Chicago Board Options Exchange, Swap.com, and Granata Decision Systems. Tuomas has published over 450 papers. His many honors include the NSF Career Award, inaugural ACM Autonomous Agents Research Award, Sloan Fellowship, Carnegie Science Center Award for Excellence, Edelman Laureateship, and Computers and Thought Award. He is a fellow of the ACM, AAAI, and INFORMS and holds an honorary doctorate from the University of Zurich. He holds a PhD and MS in computer science and a Dipl. Eng. with distinction in industrial engineering and management science.
©2017, O'Reilly Media, Inc. • (800) 889-8969 or (707) 827-7019 • Monday-Friday 7:30am-5pm PT • All trademarks and registered trademarks appearing on oreilly.com are the property of their respective owners. • email@example.com