Generative AI creates playable version of Doom game with no code

[Pelican Press 0]

This is the hidden content, please

• Sign In
• or
• Sign Up

Generative AI creates playable version of ***** game with no code

data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///ywAAAAAAQABAAACAUwAOw==

A scene from an AI-generated facsimile of the computer game *****

id software

An AI-generated recreation of the classic computer game ***** can be played normally despite having no computer code or graphics. Researchers behind the project say similar AI models could be used to create games from scratch in the future, just as they create text and images today.

The model, called

This is the hidden content, please

• Sign In
• or
• Sign Up

, was made by Dani Valevski at

This is the hidden content, please

• Sign In
• or
• Sign Up

Research and his colleagues, who declined to speak to New Scientist. According to their

This is the hidden content, please

• Sign In
• or
• Sign Up

on the research, the AI can be played for up to 20 seconds while retaining all the features of the original, such as scores, ammunition levels and map layouts. Players can ******* enemies, open doors and interact with the environment as usual.

After this *******, the model begins to run out of memory and the illusion falls apart.

The original ***** was released in 1993 and has become a popular subject for computer science projects in the years since, including attempts to

This is the hidden content, please

• Sign In
• or
• Sign Up

such as toasters, treadmills and espresso machines.

But in all those cases, the hardware is simply running the original game’s code. What GameNGen does is fundamentally different: a type of AI called a neural network has learned by observation how to recreate the game without seeing any of its code.

The researchers first created an AI model that learned to interact with ***** as a human would. That model was then tasked with playing the game over and over again while a second AI model, based on the

This is the hidden content, please

• Sign In
• or
• Sign Up

image generator, learned how hundreds of millions of inputs resulted in changes in the game state.

That second model essentially then became a copy of the game, with all of the knowledge, rules and instructions from the original code encoded in the mysterious network of artificial neurons in its own architecture. In tests, human players were only slightly better than random chance at distinguishing short clips of the game from clips of the AI simulation.

GameNGen’s creators claim in their paper that it is a proof-of-concept for games being created by a neural network rather than lines of code. They suggest that games could be generated from text descriptions or concept art, which would make production less costly than using human programmers.

This is the hidden content, please

• Sign In
• or
• Sign Up

at the University of Surrey, ***, says the idea of getting a neural network to hallucinate a game environment, and the interactions a human has with it, is an interesting step forward, but not one that will replace human game designers.

“I don’t think it’s the end of those game studios. I think what the game studios have is the imagination, the skills, to actually create these worlds, to understand gameplay, to understand engagement, understand how to draw us into a story. It’s not just the nuts and bolts, the bits and bytes,” he says. “There’s something very human about creating engaging experiences that we as human beings enjoy that, at the moment, and for the foreseeable future, will largely come from other human beings.”

Topics:

This is the hidden content, please

• Sign In
• or
• Sign Up

#Generative #creates #playable #version #***** #game #code

This is the hidden content, please

• Sign In
• or
• Sign Up

This is the hidden content, please

• Sign In
• or
• Sign Up