Benjamin Eysenbach

Empowerment measures an agent’s ability to actively control its environment. Appealing as an information theoretic quantity, empowerment is often juxtaposed with more geometric approaches to exploration, such as those that build a 3D model of the world. In this talk, I’ll discuss recent results linking empowerment and geometry, which provides an answer to a longstanding open question on the connections between empowerment and centrality. These results suggest new approaches to representation learning, exploration, and information gathering, which we demonstrate on robotics benchmarks and open-ended games.