acm-header
Sign In

Communications of the ACM

ACM News

Google Deepmind AI Navigates a Doom-Like 3D Maze Just By Looking


View as: Print Mobile App Share:
Labyrinth

Asynchronous Methods for Deep Reinforcement Learning: Labyrinth.

Credit: DeepMind

Google DeepMind just entered the 90s. Fresh off their success in playing the ancient game of Go, DeepMind’s latest artificial intelligence can navigate a 3D maze reminiscent of the 1993 shooter game Doom.

From New Scientist
View Full Article

 


 

No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account