Causal models provide a principled way to reason about the effect of actions, such as administering a new drug or implementing a policy change. This talk explores the transition from propositional to lifted causal inference, leveraging symmetries in relational domains to enable inference in compact first-order (lifted) causal models. We investigate why causality is important for decision making, introduce the foundations of causal inference, and take a look at recent advances in the field of lifted causal inference.
