The maximum score possible.
Screenshot by Aloysius Low/CNET
It’s official. Humans are now second-best at playing Ms. Pac-Man, a 1980s twist on the arcade classic, involving eating pellets and being chased by ghosts. It was rated as one of the hardest games for an AI to beat, but that didn’t stop one.
An AI from Microsoft’s Maluuba team — a Canadian deep learning startup the company acquired earlier this year — has now scored the maximum score possible of 999,990 in the Atari game, beating the human record by four times.
This was achieved using a method of reinforcement learning called Hybrid Reward Architecture. The team taught 150 AI agents to work together in parallel to master the game. Agents were rewarded for eating pellets while other agents avoided ghosts. A top agent then got feedback from the others and used a weighted average to make decisions.
It’s not just Microsoft’s AI that’s in the business of beating humans at games. Google’s champion game-playing artificial intelligence program called AlphaGo defeated one of the top Go (an ancient Chinese board game) masters last year, Lee Se-dol. This year, it defeated current Go champion Ke Jie.
Microsoft’s AI’s success at an unpredictable game could see researchers help AI tackle equally unpredictable real-world situations.
Special Reports: CNET’s in-depth features in one place.
Technically Literate: Original works of short fiction with unique perspectives on tech, exclusively on CNET.