Learning to Perceive the World Through Control: Empowerment-Based Representation Learning

ArXi:2605.30656v1 Announce Type: new In many practical reinforcement learning environments, observations are far higher-dimensional than the variables that matter for control. In this work, we ask: can we learn representations that capture only control-relevant features of the environment? We study this question through the empowerment objective, which maximizes an agent's influence over the environment and is widely used for unsupervised skill learning.