Stratego has over 10 66 possible starting positions-far more than all the stars in the universe. The number of potential game plays is mind-blowing. But that strategy faltered for Stratego, largely because of the length of game, which unlike poker, normally encompasses hundreds of moves. Stratego, in contrast, has a touch of Texas Hold ’em, a poker game DeepMind previously conquered with an algorithm. Even the most successful game-play algorithms, such as AlphaGo and AlphaZero, rely on complete information. This level of uncertainty is partly why Stratego has stumped AI for ages. Players must “balance all possible outcomes” any time they make a decision, the authors explained. Unlike chess or Go, in which each piece and movement is in view, Stratego is a game with limited information. Stratego is especially challenging for AI because players can’t see the location of their opponents’ pieces, both during initial setup and throughout gameplay. The goal is to eliminate the opposition and capture their flag. Each piece has a different name and numerical rank, such as “marshal,” “general,” “scout,” or “spy.” Higher ranking pieces can capture lower ones. Each side has 40 pieces they can place at any position on the board. The game is essentially capture the flag. In terms of complexity, Stratego is a completely different beast compared to chess, Go, or poker-all games that AI has previously mastered. As AI gains more flexible reasoning, becomes more generalized, and learns to navigate social situations, it may also spark insights into our own brains’ neural processes and cognition. Noam Brown at Meta AI, who wasn’t involved in the research.ĭeepNash’s triumph comes hot on the heels of another AI advance this month, where an algorithm learned to play Diplomacy-a game that requires negotiation and cooperation to win. “If you’re making a self-driving car, you don’t want to assume that all the other drivers on the road are perfectly rational, and going to behave optimally,” said Dr. AI systems that can easily maneuver the randomness of our world and adjust their “behavior” accordingly could one day handle real-world problems with limited information, such as optimizing traffic flow to reduce travel time and (hopefully) quenching road rage as self-driving cars become ever more present. With DeepNash, “game-playing artificial intelligence (AI) systems have advanced to a new frontier.” “Unlike chess and Go, Stratego is a game of imperfect information: players cannot directly observe the identities of their opponent’s pieces,” DeepMind wrote in a blog post. A notoriously difficult game for AI, Stratego requires multiple strengths of human wit: long-term thinking, bluffing, and strategizing, all without knowing your opponent’s pieces on the board. The result, DeepNash, toppled human experts in a highly strategic board game called Stratego. The trick was to interweave game theory into an algorithmic strategy loosely based on the human brain called deep reinforcement learning. Yet to navigate our unpredictable world, it needs to learn to make choices with imperfect information-as we do every single day.ĭeepMind just took a stab at solving this conundrum.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |