Artificial intelligence needs people's help. The best AIs are quickly mastering skills from lip-reading to playing video games, but only by learning through repeated failure. As robots take on domains like healthcare and driving, where mistakes can kill, this is no longer an acceptable approach. Fortunately, a new study suggests that with the right human oversight, it might be possible to ditch the failures. To try to train an AI without it making a mistake, Owain Evans at the University of Oxford and his colleagues started with the simple two-dimensional table tennis video game Pong.
© 2001-2024 Fundación Dialnet · Todos los derechos reservados