This video presents an introduction to the Qualitative Learner of Action and Perception, QLAP. QLAP autonomously learns a useful state abstraction and a set of hierarchical actions in continuous environments. Learning in QLAP is unsupervised. The agent begins with a very broad discretization of the world (it can only tell if the values of variables are increasing or decreasing). Using this discretization, QLAP creates a set of predictive models. Initially, these models are not very reliable, but for each one QLAP can find new discretizations to improve it. These new discretizations lead to more models creating a perception loop that leads to more accurate models and a finer discretization. The models are then converted into a set of hierarchical actions.