• Hey, guest user. Hope you're enjoying NeoGAF! Have you considered registering for an account? Come join us and add your take to the daily discourse.

Nvidia researchers re-create Pac-Man (playable) using GameGAN neural network

EviLore

Expansive Ellipses
Staff Member

Forty years to the day since PAC-MAN first hit arcades in Japan, and went on to munch a path to global stardom, the retro classic has been reborn, delivered courtesy of AI.

Trained on 50,000 episodes of the game, a powerful new AI model created by NVIDIA Research, called NVIDIA GameGAN, can generate a fully functional version of PAC-MAN — without an underlying game engine. That means that even without understanding a game’s fundamental rules, AI can recreate the game with convincing results.

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.

“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.

“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.”

We’ll be making our AI tribute to the game available later this year on AI Playground, where anyone can experience our research demos firsthand.




Exciting times.
 

Pagusas

Elden Member
Amazing, its like we are teetering on the edge of that big moment, the one where all these different areas of research converge and we finally see the formation of a new type of mind. Yeah we may be decades away (but in the grand scheme of human existence it will be a bat of an eye), but man is this an exciting frontier to watch as we get closer and closer.
 
Last edited:

Kazza

Member
Amazing, its like we are teetering on the edge of that big moment, the one where all these different areas of research converge and we finally see the formation of a new type of mind.

Even before we get to the "real" conscious AI stage, it's still going to have massive effects on the world. There is a really cool youtube channel detailing the latest advances and research by the name of Two Minute Papers. The guy recently put out a video showing that Deep Mind had now mastered 57 Atari games, including much more complex ones, such as Montezuma's Revenge:




Some of the visual AI stuff he shows in other videos is very impressive too. Just sticking to gaming for a moment, I can imagine some software not so far from now where you can just feed it real life photos and some examples of a certain graphic style you want to emulate, and the AI will recreate the photo in the graphical style you want.
 

stranno

Member
It creates his own gameplay: copies Pac-Man frame by frame.

First attempt and this AI is getting lazy already.
 
Last edited:

ReBurn

Gold Member
Robin Williams What Year Is It GIF
 
Top Bottom