AI Generates Playable Doom Game Without Coding

Recreating classic computer games with AI Doom It's playable without any computer code or graphics, and researchers on the project say it may be possible in the future to use similar AI models to create games from scratch, in the same way that we currently create text and images.

This model Game NGenIt was compiled by Dani Walewski of Google Research and his colleagues, who declined to be interviewed. New ScientistAccording to them paper According to the study, the AI ​​can play for up to 20 seconds while retaining all the features of the original, including score, ammo levels, map layout, etc. The player can attack enemies, open doors, and interact with the environment as normal.

After this period, the model's memory begins to run out and the illusion begins to break down.

original Doom It was released in 1993 and has since become a popular subject for computer science projects. Running on specially restricted hardware Toasters, treadmills, espresso machines, etc.

But in all of these 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 learns by observation how to recreate a game, without ever seeing the game's code.

The researchers first created an AI model that learned how to interact with Doom in a human-like way, then had it play the game over and over again, and then the second AI model learned how to interact with Doom in a human-like way. Stable diffusion The image generator learned how the game state changes with hundreds of millions of inputs.

The second model was essentially a copy of the game, with all of the knowledge, rules, and instructions from the original code encoded into a mysterious network of artificial neurons within its own architecture. In tests, human players were slightly better than chance at distinguishing between short clips of the game and clips of the AI ​​simulation.

In their paper, GameNGen's developers claim that this is a proof of concept that games can be created by neural networks rather than lines of code. They suggest that games can be generated from text descriptions and concept art, making them cheaper to produce than using human programmers.

Andrew Rogojski Researchers from the University of Surrey in the UK say the idea of ​​having neural networks hallucinate game environments and human interactions is an interesting step forward, but it's not meant to replace human game designers.

“I don't think it's the end of game studios. I think what game studios have is the imagination and the skill – the ability to actually create these worlds, understand gameplay, understand engagement, understand how to draw us into a story – that's not just the nuts and bolts or bits and bytes,” he says. “There's something very human about creating compelling experiences that we humans enjoy, and that's going to come primarily from other humans at the moment, and for the foreseeable future.”