Neurosymbolic Learning of Interpretable World Models
World models aim to learn compact representations of an environment from observations, enabling agents to predict future states and plan their behaviour. However, most existing approaches learn black-box representations, with limited ability to incorporate prior knowledge about the world. We introduce Concept-Grounded...
R. Andreoni, Massimiliano Ronzani, C. Ghidini et al.
· 0 citations