This game-playing AI is the new champ at Stratego
Able to defeat top-ranked human players and more efficient than other models, the new system could help decision-makers in military maneuvers or business negotiations.
A new artificial intelligence system, developed by researchers from MIT, Carnegie Mellon University, New York University, and Stanford University, has proven to be the top competitor at the board game Stratego, a game of imperfect information. This AI system, named Ataraxos, outperformed top human players and achieved a dominant 15-1-4 record against the world's best Stratego player.
Stratego, which involves two players and a large number of possible piece configurations, is often used to test the strategic thinking abilities of AI models. The researchers employed self-play reinforcement learning and efficient algorithms to create Ataraxos, enabling the AI to learn a strong blueprint strategy and refine its moves during gameplay using decision-time planning.
This innovative approach allows Ataraxos to efficiently navigate the complexity of Stratego's hidden information, making it a valuable tool for tackling real-world problems with similar challenges.
Written by urgent.news from MIT News AI's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
This story
This is one outlet's version. Read the fullest account.
- This game-playing AI is the new champ at Stratego news.mit.edu
