On the face of it, most real-world world tasks are hopelessly complex from the point of view of reinforcement learning mechanisms. In particular, due to the "curse of dimensionality", even the simple task of crossing the street should, in principle, take thousands of trials to learn to master. But we are better than that.. How does our brain do it? In this talk I will argue that the limited nature of attention is our friend, not a foe. I will show evidence for a bidirectional interaction between selective attention and reinforcement learning in which attention shapes learning processes, and at the same time we have to learn what to attend to. Time permitting, I will also talk about the orbitofrontal cortex, and the role it plays in, what I call, "shallow learning with deep representations".