The classic retro video game PAC-MAN is turning 40 this year and it’s getting an unusual but special AI treatment for its 40th anniversary. NVIDIA, in collaboration with Bandai Namco, reverse-engineered the coin-op classic using artificial intelligence (AI) to train a new AI model, called NVIDIA GameGAN, on 50,000 PAC-MAN episodes and have produced a fully functional version of the game without an underlying game engine.
GameGAN is the first neural network model that mimics a computer game engine by harnessing generative adversarial networks, or GANs. Made up of two competing neural networks, a generator, and a discriminator, GAN-based models learn to create new content that’s convincing enough to pass for the original. You may have experienced GANs by using NVIDIA GauGAN, a deep learning model developed by NVIDIA Research that turns rough doodles into photorealistic masterpieces with breath-taking ease.
GameGAN could accelerate the creative process for game developers, as it could be used to automatically generate layouts for new game levels. GameGAN can also be used by AI researchers to more easily develop simulator systems for training autonomous machines, where the AI can learn the rules of an environment before interacting with objects in the real world.
“We were blown away when we saw the results, in disbelief that AI could recreate the iconic PAC-MAN experience without a game engine,” said Koichiro Tsutsumi from BANDAI NAMCO Research Inc., the research development company of the game’s publisher BANDAI NAMCO Entertainment Inc., which provided the PAC-MAN data to train GameGAN. “This research presents exciting possibilities to help game developers accelerate the creative process of developing new level layouts, characters and even games.”
According to NVIDIA, the game will be available later this year on AI Playground, where anyone can experience this amazing research demos first-hand.
(Source: NVIDIA Blog)