Chip designer NVIDIA (NASDAQ: NVDA) has recreated the classic video game Pac Man in an unusual way. The company set up an artificial intelligence (AI) system known as NVIDIA GameGan, it supplied video clips and game control signals from 50,000 Pac Man game sessions and gave GameGan four days to generate its own version.
It worked. NVIDIA’s research team created a playable version of Pac Man.
Why make this idea unique?
You may remember how Alphabet (NASDAQ: GOOG) (NASDAQ: GOOGL) set up an AI system for playing chess with himself, from nothing but the basic rules and ending with the world’s strongest chess computer less than 24 hours later. GameGan is similar to Alphabet’s AlphaZero, but this system creates new games instead of playing existing ones.
It generated Pac Man the game is fully playable but a little rough around the edges. The graphics look even more old-school than the 1980 original, and the distinct movement patterns of each of the four ghosts have been boiled down to a single personality.
Again, there was no human input into the game’s mechanics. NVIDIA’s team asked GameGan to analyze a few thousand games and design their own rules to fit the input. That’s all.
Pac Man is an early test of an even more impressive ambition. Over time, GameGan should be able to analyze more complex games, such as first person shooter and real-time strategy games, and elements from various generated games can be combined to create entirely new gaming experiences. In addition to the high goal, NVIDIA wants to use real data to create advanced simulation systems in reality.
At the moment a new start Pac Man has been created by a neural network. It’s a pretty good start. A public release will follow soon.