Ms. Pac-Man Plays Herself

In the latest feat of artificial intelligence (AI), researchers have taught AI agents to play Ms. Pac-Man - and sometimes do it better than humans.

The researchers explain that games are ideal test environments for reinforcement learning (RL). Since the late 1950s, RL has been tested in classical games, such as checkers, backgammon, and chess. Since the 2000s, researchers have begun testing RL on modern computer games, such as the role-playing game Baldur's Gate, the strategy game Wargus, and Tetris.

Read Full Story >>
The story is too old to be commented.