I am looking for a gentle introduction (videos, lecture notes, tutorials, books) on reinforcement learning (MDPs) involving continuous states (or very large cardinality of state space). In particular, I am looking for ways on how to deal with them, including a good discussion on the build up to important and relevant concepts.
Most of the books I encountered just state that we need function approximation, and then moved on to talk about radial basis functions. These ideas, however, are very abstract and are not easy to understand. For example, why specifically those functions?
