Italian researchers trained a neural network to generate new Doom (1993) game levels. The feat was achieved by training two deep-learning neural networks, they were fed 1,000 existing Doom levels to figure out how a Doom level should look like. The result is an AI agent that can theoretically create an infinite number of Doom levels. More info at DigitalTrends.
“There are no explicit bias encoded in the networks that generate the levels, but we expected — and found in our analysis — the networks generate levels that share similarities with levels used for training,” Daniele Loiacono, an assistant professor at Italy’s Politecnico of Milano, told Digital Trends. “Accordingly, choosing the set of levels to use for training makes it possible to affect the quality and the characteristics of the levels generated.”
The work may result in better design tools, which can speed up game content creation by creating stuff automatically. This would free up human time to work at a higher level of abstraction.