In order to navigate the world, an autonomous agent must build a causal model to understand the effects of its actions. In many tasks (automated car driving, automated medicine), collecting causal data, by performing arbitrary actions for the sake of measuring their effect (interventions), can be impractical, expensive and even unethical. On the other hand, collecting data by observing human agents (observations), is often much cheaper, but it does not allow for measuring causal effects. The objective of this project is to expand the capabilities of current reinforcement learning algorithms to combine and exploit both interventional (causal) and observational (non-causal) data in a correct and efficient way, in order to benefit from the abundance of observational data in the world.