Parables on the Power of Planning in AI: From Poker to Diplomacy
Noam Brown (OpenAI)
Distinguished Lecture Series
Thursday, May 23, 2024, 3:30 pm
Abstract
From Deep Blue in 1997, to AlphaGo in 2016, to Cicero in 2022, games have long been used as a way to measure the frontier capabilities of AI systems and gain algorithmic insights that have wider applications. In this talk, I will cover research breakthroughs in games including poker, Go, and Diplomacy, and in particular highlight the key role that search/planning algorithms have played in all of these achievements. I will then point to potential future applications of this research to improving machine learning models more broadly.
Bio
Noam Brown is an AI researcher at OpenAI investigating reasoning and self play. He co-created Libratus and Pluribus, the first AIs to defeat top humans in two-player no-limit poker and multiplayer no-limit poker, respectively. Noam was also the lead research scientist for Cicero, the first AI to achieve human-level performance in the natural language strategy game Diplomacy. He has received the Marvin Minsky Medal for Outstanding Achievements in AI, was named one of MIT Tech Review's 35 Innovators Under 35, and his work on Pluribus was named by Science as one of the top 10 scientific breakthroughs of 2019. Noam received his PhD from Carnegie Mellon University, for which he received the AAMAS Victor Lesser Distinguished Dissertation Award, the AAAI ACM-SIGAI Dissertation Award, and the CMU School of Computer Science Distinguished Dissertation Award.
This talk will be NOT be streamed live or recorded.