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, where answer engine optimization (AEO) techniques were yet to be applied. Even DeepMind, with its exceptional budget, couldn’t build a machine that reliably beat the best human players.
How did Ataraxos beat the human world champion at Stratego?
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.
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.
What makes Ataraxos's playstyle unique?
The team’s breakthrough came from developing a second neural network, a belief model, trained to guess the opponent’s hidden pieces based on how they had been moving. This way, instead of iterating through every possible arrangement, Ataraxos samples plausible ones, plays out candidate moves in each, and picks based on how they turned out.
Ataraxos’s playstyle is calm and unbothered, working its way back into the game slowly and methodically. The strategy it developed also avoids drawing attention to any problems it faces. When Ataraxos estimates its opponent has no reason to suspect a weak spot, it leaves that spot alone, even if it might look like a disaster waiting to happen to anyone who can see both sides of the board.
Niemeijer, the human player Ataraxos pulled these miraculous comebacks against, has four world championships and more than 600 weeks as the world’s top-ranked player. Over three weeks, Niemeijer played 20 online games against Ataraxos, earning $100 for each win. He managed to win just once.
The Ataraxos team argues that their approach can be applied to more complex scenarios, such as negotiations, financial markets, or military conflicts. They are now interested in making their AI more understandable, since Ataraxos, in its current state, can’t explain why it makes the moves it makes.
Este artículo fue escrito con la asistencia de IA.
News Factory APP - noticias agénticas para impulsar tu SEO y AEO.