MIT AI Beats Top Stratego Players

Researchers from MIT, Carnegie Mellon, NYU and Stanford built Ataraxos, an AI that defeated the world's top Stratego player 15-1-4 and went 39-2 against world championship players. It uses self-play reinforcement learning and decision-time planning to handle hidden information, training far more efficiently than DeepMind's DeepNash. The work appears in Nature.