“You can think of curiosity as a kind of reward which the agent generates internally on its own, so that it can go explore more about its world,” Agrawal said. This internally generated reward signal ...

In March, a computer achieved what many thought impossible when it won a best of five series against world-class go champion Lee Sedol. The victory by the DeepMind computer was the most significant ...

But this carrot-and-stick approach to machine learning has its limits, and artificial intelligence researchers are starting to view intrinsic motivation as an important component of software agents ...