Robot masters new skills through trial and error
Berkeley CA (SPX) May 28, 2015 - Researchers at the University of California, Berkeley, have developed algorithms that enable robots to learn motor tasks through trial and error using a process that more closely approximates the way humans learn, marking a major milestone in the field of artificial intelligence. They demonstrated their technique, a type of reinforcement learning, by having a robot complete various tasks - ... more
No comments:
Post a Comment