An artificial intelligence (AI) system tasked with playing retro 1980s arcade game Q*bert managed to secure impossibly high scores by exploiting an ancient bug.
The bot was programmed to use evolutionary strategy (ES) algorithms, which includes machine learning (ML) and allows the AI to learn, adapt, and change tactics depending on the situation and other players.
ES and reinforcement learning (RL), which is based on behavioral psychology and revolves around a simple reward system, have already been used to beat human players in games including Chess and Texas Hold ’em.
