A little over a year ago, Nvidia GameGAN was presented to the public, a neural network that had been able to create its own version of Pac-Man simply by watching videos of the game. Now they are trying to do the same with Grand Theft Auto .
With a demo published on GitHub for the enjoyment of the connoisseur and the curious, Nvidia has shown that its neural network can learn everything necessary about GTA V to recreate a small portion of the game including all its details and mechanics.
From the control of the vehicle to often imperceptible details such as the sun’s reflection on the rear window or the shadow on the asphalt, the most impressive thing about GAN Theft Auto is not that it manages to replicate a game like this with a very nappy look, but that is able to do it without generating any type of code by a human.
That it still has a long time to become a completely useful tool at the development level is more than evident, of course, but it is no less impressive to have in your hands the demo of a game that has been created by an AI .
Advances in artificial intelligence have already left us with sweet potato paste on more than one occasion with GTA V as the protagonist. Just a few weeks ago we saw how Intel managed to give the game a photorealistic appearance without human intervention, but this from Nvidia seems even crazier.
GTA Online guides
- GTA Online guide: tricks, secrets and the best tips
- 19 tips and tricks for GTA V after playing seven years that you would give to a newbie
- How to get free money in GTA Online
- GTA Online: Cayo Perico map with the location of all the daily treasure chests
- GTA Online: Cayo Perico map with the location of all motorcycles
- GTA Online: how to save your money from your mobile or bank so that they do not rob you
- The best weapons in GTA Online: stats, tier list and how to get them
- The most expensive weapons GTA Online: statistics and how to get them
- The best assault rifles in GTA Online: tier list, stats and how to get them
