I've recently been trying to take on RL again (bit of redemption after my
glaring defeat to box2d car racing 2 years ago!).  In this pursuit I
came across some new analogies that were extremely useful to me in
creating a mental model for how some of these techniques work.  Thought
they may be useful to some of your students.

This commit
- adds an analogy for the purpose of the target network
- emphasizes the _reason_ experience replay works
- adds a section on advanced RL techniques used to overcome sparse
reward functions