Learning Abstract World Models with a Group-Structured Latent Space

ArXi:2506.01529v2 Announce Type: replace Learning meaningful abstract models of Marko Decision Processes (MDPs) is crucial for improving generalization from limited data. In this work, we show how geometric priors can be imposed on the low-dimensional representation manifold of a learned transition model. We incorporate known symmetric structures via appropriate choices of the latent space and the associated group actions, which encode prior knowledge about invariances in the environment.