Researchers have overcome one of the major stumbling blocks in artificial intelligence with a program that can learn one task after another using skills it acquires on the way.
Developed by Google’s AI company, DeepMind, the program has taken on a range of different tasks and performed almost as well as a human. Crucially, and uniquely, the AI does not forget how it solved past problems, and uses the knowledge to tackle new ones.
The AI is not capable of the general intelligence that humans draw on when they are faced with new challenges; its use of past lessons is more limited. But the work shows a way around a problem that had to be s
One reason the AI did not nail each game was that it sometimes failed to appreciate how important certain connections were for its playing strategy. “We know that sequential learning is important, but we haven’t got to the next stage yet, which is to demonstrate the kind of learning that humans and animals can do.” Kirkpatrick said.
[GUARDIAN]
