Microsoft-backed artificial intelligence can beat your 'Ms. Pac-Man' high score

The method used to master Ms. Pac-Man could help demonstrate the benefits of a divide-and-conquer approach in real-world applications. A team of researchers have managed to develop an artificial intelligence capable of mastering the arcade classic Ms. Pac-Man. Maluuba -- a Canadian deep learning startup that was acquired by Microsoft in January 2017 -- used a divide-and-conquer technique to empower its system to complete the Atari 2600 version of the game with a perfect score of 999,990. Maluuba's approach is interesting, because it breaks down the strategies and maneuvers required to beat the game into their component parts. Various different agents focus on one job and one job alone, while an agent put in charge of managing from the top makes high-level decisions about what actions should be prioritized.