Researchers developed superhuman AI for Stratego, a board wargame with hidden information, using self-play reinforcement learning and test-time search. The achievement surpasses previous failed attempts and requires only thousands of dollars rather than millions, establishing new benchmarks for AI performance on classical games.
Researchers from Carnegie Mellon, MIT, NYU, and Stanford developed Ataraxos, an AI that defeated top Stratego player Pim Niemeijer 15-1, solving a game that had resisted AI for decades. Stratego's complexity stems from massive hidden information across thousands of moves and the need to balance bluffing, challenges that earlier AI systems like DeepMind's DeepNash could not overcome.