NVIDIA AI creates fully functional Pac-Man by watching gameplay videos

Another impressive feat from NVIDIA's Research unit. The company's GameGAN artificial intelligence model was able to recreate a fully functional Pac-Mac game without access to the underlying game engine. The model was trained using 50,000 gameplay videos of the game and it managed to cook up its own version of the game. The Pac-Man created by GameGAN looks and feels like the real thing, but it does have a noticeably lower resolution.

NVIDIA speculates GameGAN could be used to speed up game development.

“This is the first research to emulate a game engine using GAN-based neural networks,” said Seung-Wook Kim, an NVIDIA researcher and lead author on the project. “We wanted to see whether the AI could learn the rules of an environment just by looking at the screenplay of an agent moving through the game. And it did.”

As an artificial agent plays the GAN-generated game, GameGAN responds to the agent’s actions, generating new frames of the game environment in real time. GameGAN can even generate game layouts it’s never seen before, if trained on screenplays from games with multiple levels or versions.

This capability could be used by game developers to automatically generate layouts for new game levels, as well as by AI researchers to more easily develop simulator systems for training autonomous machines.

Full details at the NVIDIA blog.