Learned representations of dynamical systems reduce dimensionality, potentially supporting downstream reinforcement learning (RL). However, no established methods predict a representation's suitability for control and evaluation is largely done via downstream RL performance, slowing representation design. Towards a principled evaluation of representations for control, we consider the relationship between the true state and the corresponding representations, proposing that ideally each representation corresponds to a unique true state. This motivates two metrics: temporal smoothness and high mutual information between true state/representation. These metrics are related to established representation objectives, and studied on Lagrangian systems where true state, information requirements, and statistical properties of the state can be formalized for a broad class of systems. These metrics are shown to predict reinforcement learning performance in a simulated peg-in-hole task when comparing variants of autoencoder-based representations.
View on arXiv