Why is Reinforcement Learning so Curious?

So far we assumed that all the data is given to us and that we don't really have much of a choice of what we do. For instance, when Google wants to display an ad for the query'cat' it has thousands of possible ads at its disposition, ranging from kitty litter to catsuits. Which ad gets the most clicks depends very much on the ad, the user, and the context. Hence it must try out different versions to determine which ones are best. Doing this brute force is very expensive (nobody wants to see too many catsuit ads).