Home

I am a PhD student in Computer Science at Carnegie Mellon University advised by Professor Tuomas Sandholm. My research combines reinforcement learning and game theory to produce AIs capable of strategic reasoning in large imperfect-information multi-agent interactions.

I have applied my research to making the first AI to defeat top humans in no-limit poker. With my advisor, I created Libratus, which decisively defeated four of the world's best human poker professionals in a Man vs. Machine competition. I also co-created its predecessor Claudico, as well as BabyTartanian8 and Tartanian7, which have won the last two Annual Computer Poker Competitions.

Before CMU, I worked at the Federal Reserve Board in the International Financial Markets section, where I researched algorithmic trading in currency markets. Before that, I developed algorithmic trading strategies for equity markets.

News: I will be at NIPS 2017, where we won Best Paper!

Contact information: noamb <at> cs <dot> cmu <dot> edu