The researchers used a novel method that allowed the AI to learn to play Stratego by itself while developing its own strategies. The game only ends when one player’s flag piece is captured or they can no longer make any legal moves.īut DeepNash has been able to pull it off. Some of the other playable pieces include bombs (powerful but immobile), scouts (that can move more than one square at once), and miners (who can defuse bombs) which all add to the tactical complexity. When you are planning an attack, you don’t know if the defender is a high-ranked Marshal that will beat almost all your pieces or a lowly Sergeant that can be taken out by a Lieutenant or Captain. Both players have 40 pieces with different tactical values that can are deployed at the start of the game-the catch is that you can’t see what your opponent’s pieces are and they can’t see what yours are. Each game takes place over a 10 x 10 gridded board with two 2 x 2 square lakes blocking the middle of the board. The goal is to move across the board and capture the other player’s flag piece. Stratego is a game with two distinct challenges: it requires long-term strategic thinking (like chess) and also requires players to deal with incomplete information (like poker). It’s a huge and surprising result-at least to the Stratego community. A new AI called “DeepNash” has mastered Stratego, one of the few iconic boardgames where computers don’t regularly trounce human players, according to a paper published this week.
0 Comments
Leave a Reply. |