We love Doom, every old school gamer loves Doom, and now researchers from Italy's Politecnico of Milano have used two deep-learning neural networks to create an infinite number of new levels for the 1993 shooter. Digital Trends is reporting that the neural networks were shown 1,000 existing Doom levels, which game them the ability to learn the features found in popular ones, and use that for the basis of generating new ones.
Incredible stuff, however the levels shown in the demo video don't look all that great to me. I can definitely see the potential, but at the same time the last thing we need is game developers getting even more lazy.
"We think that this work, as well as several recent works in the game research literature, suggest that it would be possible very soon to develop better design tools, where A.I. could assist human designers with the game content creation," Loiacono said. "Such 'intelligent design tools could save time for human designers and, at the same time, allow them to work at a higher level of abstraction. Our other work deals with using A.I. to generate game content, including tracks for racing games, 3D assets, weapons and maps for FPS, and levels for platformers. In particular, this approach could be applied to generate maps also for real-time strategy, multiplayer online battle arena, and RPG games."
Incredible stuff, however the levels shown in the demo video don't look all that great to me. I can definitely see the potential, but at the same time the last thing we need is game developers getting even more lazy.
"We think that this work, as well as several recent works in the game research literature, suggest that it would be possible very soon to develop better design tools, where A.I. could assist human designers with the game content creation," Loiacono said. "Such 'intelligent design tools could save time for human designers and, at the same time, allow them to work at a higher level of abstraction. Our other work deals with using A.I. to generate game content, including tracks for racing games, 3D assets, weapons and maps for FPS, and levels for platformers. In particular, this approach could be applied to generate maps also for real-time strategy, multiplayer online battle arena, and RPG games."