NVIDIA creates artificial intelligence capable of recreating Pac-Man from scratch: it was enough to train him with 50,000 games – InTallaght

Original article was published on artificial intelligence

Pac-Man was released on May 22, 1980, the legendary video game of the eater that brought about a real revolution first in arcades and later on computers and consoles.

His legacy has been enormous, and now NVIDIA has wanted to pay a singular tribute to the Bandai Namco title. For this they have created an artificial intelligence system that simply playing 50,000 games Pac-Man has recreated the game from scratch, by himself, respecting the mechanics and rules of the game.
<! – more →

No code is generated, images are generated

The system created by NVIDIA has been baptized as GameGAN, and as its name indicates, makes use of antagonistic generative networks (GAN, Generative Adversarial Networks) a type of algorithm that takes advantage of the unsupervised learning philosophy.

This approach to this type of problem is already familiar to NVIDIA, which in the past has used it in other areas such as the artistic one with GauGAN or the generation of animal images from stuffed animals with GANimal. The idea is that the system learns the rules of the game simply by observing it over and over again.

According to NVIDIA GameGAN it is the first neural network model that emulates the behavior of a video game engine. It makes use of two neural networks that compete with each other (one generator and the other discriminator), and ends up creating new content that emulates the original content they were watching.

The idea is relatively simple: as the artificial agent plays the game generated by this unique engine, GameGAN responds to those actions by generating the frames in real time. This engine does not generate code that is then executed, but basically it generates frames in a coherent way as the different actions that occur in the game are recognized and evaluated.

GameGAN wants to go beyond Pac-Man

By observing the development of these games, the general model of the static elements of the environment, but also respects its rules. For example Pac-man can’t break through the walls or that when passing over a ball, he eats it.

With this system it would therefore be possible to offer developers a tool to automatically create new levels for their games, but it also allows AI researchers to have a tool to develop simulation systems to train autonomous machines.

The creators of this system highlighted that with GameGAN they could “have an artificial intelligence that learn to emulate the rules of driving and the laws of physics simply by watching videos and seeing how agents make certain decisions in their environment. ”

The Pac-Man game created by this artificial intelligence will be available soon on the NVIDIA AI Playground website thanks to the agreement with Bandai Namco for anyone to enjoy.