DeepMind’s latest artificial intelligence, DeepNash, has developed enough to beat almost all human players at Stratego. Stratego is a war game that has two players going after the enemy’s flag.
Stratego needs players to work out the identity of each other’s 40 game pieces, which are concealed from sight. This sets it apart from other board games like Go and chess, which former DeepMind AIs have learned to master as well.
Stratego is a “game of imperfect information,” as DeepMind explains on its website, which means each player needs to “balance all possible outcomes when making a decision.”
Again, these features make it more complicated than other games. In numbers, Go has ten to the power of 360 possible game states which is far more than both poker or chess. However, Stratego has ten to the power of 535.
According to DeepMind, DeepNash has become so good at Stratego that it’s “reached an all-time top-three ranking among human experts on the world’s biggest online Stratego platform, Gravon.”
The AI developed an “unpredictable strategy” to make sure its human opponent was kept guessing, which comprosed making decoy deployments to shake them off its path. It even learned how to bluff its opponent by playing low-ranking pieces, portraying that they were worthmore than they did!
“The level of play of DeepNash surprised me,” said Vincent de Boer, coauthor of a new paper about the AI published in the journal Science, who also is a former Stratego World Champion, in a statement. “I had never heard of an artificial Stratego player that came close to the level needed to win a match against an experienced human player.”