The Doppler Quarterly Spring 2018 | Page 41

The Most Recent Milestone While both chess and Go have their own respective levels of complexity, they both involve perfect infor- mation. In other words, both players can see all the pieces on the board at all times. The game of heads-up (or two-player), no-limit Texas Hold'em, on the other hand, is a game of imperfect information. A player cannot see the two face down cards dealt to the other player and the three cards turned up over the three rounds of play after the deal are unknown. To provide a sense for this complexity, when you're dealt into a game, the cards you're dealt and the communal cards that appear are one possibility of 10^160. That's one followed by 160 zeroes, or more than the number of atoms in the universe. This represents a problem that cannot readily be brute-forced by simply throwing compute power at it. Around the same time that AlphaGo Master was mak- ing strides against its predecessor AlphaGo Lee in January 2017, an AI program named Libratus was pit- ted against four top human poker players - Jason Les, Dong Kim, Daniel McAulay and Jimmy Chou. After 20 days of play and 120,000 hands of poker, Libratus emerged as the winner. Carnegie Mellon Professor Tuomas Sandholm and his graduate students developed Libratus as a successor to a prior version called Claudico (originally called Tartanian). Libratus used three different approaches that worked together, and this was its key differentiator. First, it used a technique called reinforcement learn- ing in which the program used random trial and error to learn by playing a game against itself, via an algo- rithm known as counterfactual regret minimization. Note that this technique appears to have subse- quently been adopted by the latest versions of AlphaGo (AlphaGo Zero and AlphaZero). The tech- nique ends up testing such a wide range of approaches that it finds some optimized strategies that humans would otherwise not think to try. In certain cases, this actually ended up throwing human opponents off. AlphaGo is a more com- plex game than chess with a 19x19 board and the added complexity of pieces being flipped when surrounded by an opponent's stones. SPRING 2018 | THE DOPPLER | 39