Submit Video

An AI Just Made A Grand Theft Auto Game, And It Looks Wild

| Last updated 

An AI Just Made A Grand Theft Auto Game, And It Looks Wild

If you've played Grand Theft Auto V once, you've played it a thousand times. Yet, seeing the iconic state of San Andreas through the "eyes" of an artificial intelligence is actually amazing.


If Grand Theft Auto V was a beachgoer, it'd be the one who brought a sturdy camping chair, a blanket, a big ol' umbrella, several books and a hefty cool bag packed with beverages of all sorts. In other words, it's here for the long haul and it wants you to know it's not giving up this spot, come hell or high tides. Though we may gripe and grouse that we've not gotten Grand Theft Auto VI yet yet, players are still discovering ways to plumb the current game for all of its goodness, almost seven years on from its original release. One very adept and agile player managed to complete the entirety of Grand Theft Auto V without taking a single hit. Considering how chaotic that game can be, that's incredibly impressive. And, there was the developer that fixed the Grand Theft Auto Online loading times that seem to stretch for aeons, and Rockstar Games gave them a tidy $10,000 and told them not to spend it all in one go.

While you're here, check out these timeless wins and fails in Grand Theft Auto V.



Last month, an Intel Labs undertaking brought machine learning techniques to Grand Theft Auto V, transforming its visuals into an extremely realistic version of itself. Like Imogen said, it's a little like watching a dashcam. And now, in a second interesting yet ultimately useless project, we can see what Grand Theft Auto V would look like if an artificial intelligence made it. Harrison Kinsley, also known as sentdex on YouTube and the author of Neural Networks from Scratch, uploaded a video of GAN Theft Auto, the version of the game created by Kinsley and fellow programmer Daniel Kukieła's GameGAN.

GAN stands for generative adversarial network and within it, it contains two competing neural networks. The first is the generator: it's got the job of consuming a sample dataset and then generating content as per the data in the sample. The second is the discriminator: it takes the generated content and compares it against the original sample, subtracting what is too different so that the generator produces content that is more and more accurate to the sample.

The result, while fascinating, does look like you're in the throes of one hell of a migraine. If you're fortunate enough to have never been afflicted by one, this is what all of the fuss is about. "Every pixel you see here is generated from a neural network while I play," explained Kinsley in the video. "The neural network is the entire game. There are no rules written here by us or the [RAGE] engine." It's even able to reproduce how distance makes the mountains larger or smaller depending on how far away the car is from them, which was surprising to the team. It's playable through this link, if you want to give it a whirl.

Featured Image Credit: Rockstar Games, Studio Canal

Topics: Rockstar Games, News, Grand Theft Auto

Imogen Donovan
More like this

Chosen for YouChosen for You

Resident Evil

Leon S Kennedy Actor Wants A ‘Resident Evil 4’ Movie

3 days ago

Most Read StoriesMost Read