Children of the 1980s spent hours perfecting the art of playing Namco’s Pac-Man computer game. And now computers are teaching each other to play the popular game, which sees a player navigating a maze, trying to gobble up pellets while avoiding four colourful enemies. Researchers have managed to develop a method to allow a computer to give advice and teach skills to another computer in a way that mimics how a real teacher and student might interact – and are demonstrating it with video games.
Video games can be educational — for computers. Researchers at Washington State University developed an algorithm that helps computers learn and teach each other by playing Pac-Man, an iconic video game that has eaten up the spare time of gamers since the 1980s. Advances in robot intelligence could potentially lead to robots teaching humans. Matthew E. Taylor, an expert in artificial intelligence at WSU, published these findings online in the journal Connection Science. The virtual robots, nicknamed “student agent” and “teacher agent,” learn from each other as the student agent navigates through a dizzying maze trying to outrun four colorful ghosts all while gobbling up pellets. When the teacher agent detects its disciple is in trouble, it jumps in to give advice.
