With most information hidden, the game Stratego had stumped AI, until now
Deep Blue took down Garry Kasparov at chess in 1997, AlphaGo beat Lee Sedol at Go in 2016, and poker bots have been beating professionals for years. But one classic game called Stratego held out. Even DeepMind, with its exceptional budget, couldn't build a machine that reliably beat the best human players. Now, a team of researchers from Carnegie Mellon, MIT, New York University, and Stanford University has done it. Their AI, called Ataraxos, beat Pim Niemeijer, arguably the best Stratego player
Get smart on it
Researchers have created an AI system that beats the best human players at Stratego, a board game where most piece identities remain hidden until pieces clash in battle. The breakthrough matters because Stratego had resisted AI solutions despite successes in chess, Go, and poker, due to its combination of massive hidden information spread across thousands of moves and the strategic need to bluff effectively. The key innovation was adding a second neural network that guesses opponent positions based on their movements, allowing the AI to sample plausible scenarios rather than evaluating all possible arrangements. The system was trained efficiently on consumer-grade hardware for a fraction of the cost of previous attempts, suggesting the techniques could apply to real-world problems involving incomplete information and strategic opponents.
Related news
Opus 5.5 loves to tell you ‘this matters’ (and other AI writing tells)
Opus 5.5’s biggest tell is the word “dependable,” which pops up 23 times more often than in human samples.
Open TTS Leaderboard: Scalable Evaluation for Multilingual Text-to-Speech and Voice Cloning
Comparing speech synthesis systems across languages and voices has lacked standardized metrics, making it harder to track progress in this rapidly advancing field.
