The field of artificial intelligence has had a number of high-profile successes in the domain of perfect-information games like chess or Go where all participants know the exact state of the world. But real-world strategic interactions typically involve hidden information, such as in negotiations, cybersecurity, and financial markets. Past AI techniques fall apart in these settings, with poker serving as the classic example. Pluribus is an AI that, in a 10,000-hand competition, defeated a collection of elite human professionals in six-player 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 I will explain why poker was such a difficult challenge for AI, and the advances in Pluribus that overcame those challenges. I will conclude by discussing what comes next for multi-agent artificial intelligence research.
Noam Brown is a Research Scientist at Facebook AI Research. His research combines computational game theory and machine learning to develop AI systems capable of strategic reasoning in large imperfect-information multi-agent settings. He has applied this research to creating Libratus and Pluribus, the first AIs to defeat top humans in two-player no-limit poker and multi-player no-limit poker, respectively. Libratus was one of 12 finalists for Science Magazine's Scientific Breakthrough of the Year and Pluribus was featured on the cover of Science Magazine. Noam has also received the 2017 Allen Newell Award for Research Excellence, the 2019 Marvin Minsky Medal for Outstanding Achievements in AI, and was named one of MIT Tech Review's 35 Innovators Under 35.