This popular game has an enormous game tree on the order of 10 535 nodes, i.e., 10 175 times larger than that of Go. Stratego is one of the few iconic board games that Artificial Intelligence (AI) has not yet mastered.
from scratch, up to a human expert level. “We also hope R-NaD can help unlock new applications of AI in domains that feature a large number of human or AI participants with different goals that might not have information about the intention of others or what’s occurring in their environment,” DeepMind’s researchers detailed.We introduce DeepNash, an autonomous agent capable of learning to play the imperfect information game Stratego 3 3 3 Stratego is a trademark of Jumbo Diset Group, and is used in this publication for information purposes only.
Stratego game play series#
This means creating initial deployments varied enough to prevent its opponent spotting patterns over a series of games.”ĭeepMind believes that the AI techniques it developed to build DeepNash could be applied to other tasks besides playing “Stratego.” According to the Alphabet unit, the AI system’s ability to develop an optimal course of action in complex situations could potentially be applied in fields such as traffic management. “DeepNash developed an unpredictable strategy. “To achieve these results, DeepNash demonstrated some remarkable behaviours both during its initial piece-deployment phase and in the gameplay phase,” DeepMind researchers detailed in a blog post. In another evaluation, DeepNash played an online version of “Stratego” and achieved a win rate of 84% against expert human players. To evaluate DeepNash’s performance, DeepMind had it play a series of matches against several earlier AI systems configured to play “Stratego.” DeepNash won more than 97% of the matches, according to the Alphabet unit. In such a situation, both players make the optimal combination of game moves during the match.īy studying what would happen if its opponent would make the optimal combination of moves, DeepNash can develop an action plan that maximizes its chance of winning. A Nash equilibrium is a situation where each “Stratego” player uses the game strategy that has the highest chance of defeating the other player’s strategy. That method forms the basis of the DeepNash system DeepMind detailed this week.Īccording to DeepMind, DeepNash develops a plan for winning “Stratego” matches by simulating a so-called Nash equilibrium. To address that limitation, DeepMind’s researchers developed a new AI method dubbed R-NaD that draws on the mathematical field of game theory. Chess has a game tree complexity number of 10 to the power of 123, while in “Stratego,” that number increases to 10 to the power of 535.Īccording to DeepMind, traditional methods of teaching AI systems to play board games can’t be applied well to “Stratego” because of its complexity.
The number of potential tactics that players can use in a board game is measured with a metric known as the game tree complexity number. This dynamic makes playing the game difficult for AI systems.Īnother source of complexity is that there are more possibilities to consider than in chess. A player might know that the other player has placed a game piece on a certain section of the board, but not which specific game piece was placed there. In “Stratego,” each player has only limited information about the other player’s game pieces. But there are a number of differences between the two games that make “Stratego” more complicated than chess. Players receive a collection of game pieces that, like chess pieces, are maneuvered around the board until one of the players wins. “Stratego” is a two-player board game that is similar to chess in certain respects. The Alphabet unit says that DeepNash achieved a win rate of more than 84% in matches against expert human players. Alphabet Inc.’s DeepMind unit has developed a new artificial intelligence system capable of playing “Stratego,” a board game considered more complex than chess and Go.ĭeepMind detailed the AI system, which it dubs DeepNash, on Thursday.
0 kommentar(er)
