One Step Closer To The Matrix: Ai Defeats Human Champion In Street Fighter — With A Revolutionary Type Of Memory It Used Makes It Even More Powerful

Researchers from the Singapore University of Technology and Design (SUTD) have developed a new software powered by reinforcement learning and phase-change memory to understand complicated movement design. The AI system was trained for two days and was able to beat a human participant in the game Street Fighter Champion Edition II. This work has implications for movement science and can be applied to robotics and autonomous vehicles. It is part of a larger trend of AI systems competing with human players in different kinds of games.