MIT's Ataraxo AI beats top Stratego players with self-play and decision-time planning

nordicinst · x · 2026-09-30

MIT News reports that Ataraxos, developed by researchers at MIT, CMU, NYU, and Stanford, defeats top-ranked human Stratego players while using fewer resources than other models. It combines self-play with decision-time planning to scale to imperfect-information games, an area where poker-style AI techniques break down due to an explosion of possible game states. Researchers see potential applications in military maneuvers and business negotiations.

Original post →

More from Research

Research channel →