Tag
A team from CMU, MIT, NYU, and Stanford created Ataraxos, an AI that beat the best Stratego player in history 15-1-4 while training on just 16 GPUs, overcoming the game's massive hidden information and long-horizon challenges that stumped DeepMind's DeepNash.
Researchers from MIT, Carnegie Mellon, NYU, and Stanford developed an AI that decisively defeats top human Stratego players, a game of hidden information, using efficient training methods far cheaper than prior approaches like DeepMind's. The system, published in Nature, generalizes to other strategic games and could aid real-world decision-making under uncertainty such as business negotiations and cybersecurity.