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 of all time, 15 games to one, with four draws. And it took just 16 GPUs and a few thousand dollars to train it.

Hidden armies

In Stratego, each player gets 40 pieces representing military ranks, from a marshal down to a spy, plus bombs and a flag. You win by capturing the opponent's flag. Your opponent knows where your pieces are, but not what they are. Identities are revealed only when two pieces collide in battle—the weaker one is removed, and the identity of the winner is revealed. That makes Stratego an imperfect-information game, just like poker, which computers cracked years ago. “There's something super distinctive about Stratego, which is that it is a massive amount of hidden information that unfolds over a very long time scale,” said Eugene Vinitsky, a researcher at NYU and co-author of the study.

Read full article

Comments

28:T429,{"@context":"https://schema.org","@type":"NewsArticle","@id":"https://nvdium.com/en/articles/693717200#article","url":"https://nvdium.com/en/articles/693717200","headline":"With most information hidden, the game Stratego","description":"Adding in a second neural network that guesses the identity of hidden pieces was key.","datePublished":"2026-10-01T17:12:14.634Z","dateModified":"2026-10-02T17:39:13.733Z","mainEntityOfPage":"https://nvdium.com/en/articles/693717200","isAccessibleForFree":true,"inLanguage":"en","isPartOf":{