AI for Imperfect-Information Games: Beating Top Humans in No-Limit Poker
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 grand challenge problem for AI in general. In this talk I will explain why imperfect-information games are fundamentally more difficult than perfect-information games and the advances in Libratus and my later work that overcome those challenges. In particular, I will describe new methods I 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. I will also discuss my work on combining these algorithms with function approximation, which allows the algorithms to be easily applied to other large-scale games.
Noam Brown is a PhD student in computer science at Carnegie Mellon University advised by Tuomas Sandholm. His research combines computational game theory and machine learning to develop AI systems capable of strategic reasoning in large imperfect-information multi-agent interactions. He has applied this research to creating Libratus, the first AI to defeat top humans in no-limit poker, which was published in Science and was one of 12 finalists for Science Magazine's Scientific Breakthrough of the Year. Noam has received a NeurIPS Best Paper award in 2017, the 2017 Allen Newell Award for Research Excellence, an AAAI 2019 Outstanding Paper Honorable Mention, and the 2019 Marvin Minsky Medal for Outstanding Achievements in AI. He is supported by an Open Philanthropy Project AI fellowship and a Tencent AI Lab fellowship.