Faculty Recruiting Support CICS

AI for Imperfect-Information Games: Beating Top Humans in No-Limit Poker

14 Feb
Thursday, 02/14/2019 4:00pm to 5:00pm
Computer Science Building, Room 151
Special Event
Speaker: Noam Brown

ABSTRACT: Despite AI successes in perfect-information games, the hidden information and large size of no-limit poker have made the game difficult for AI to tackle. Libratus is an AI that, in a 120,000-hand competition, decisively defeated four top professionals in heads-up no-limit Texas hold'em poker, the leading benchmark for imperfect-information games and a long-standing challenge problem for AI in general. In this talk Noam will explain why past techniques intended for perfect-information games break down in imperfect-information games, and the advances in Libratus and his later work that overcome those challenges. In particular, he will describe new methods he developed for state-of-the-art equilibrium finding and real-time search in imperfect-information games. These techniques all have theoretical guarantees in addition to strong empirical performance. Noam will also discuss his work on combining these algorithms with function approximation, which allows the algorithms to be easily applied to other large-scale games.

Bio: I am a PhD student in Computer Science at Carnegie Mellon University advised by Professor Tuomas Sandholm. My research combines computational game theory and machine learning to produce artificial intelligence capable of strategic reasoning in large imperfect-information multi-agent interactions. Before CMU, I worked at the Federal Reserve Board in the International Financial Markets section, where I researched algorithmic trading in financial markets. Before that, I developed algorithmic trading strategies.

There will be a reception in CS 150 at 3:30 p.m.

Faculty Host