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?

  • $\begingroup$ You should probably mention the books that you encountered that do not explain the topics in the way you want so that people do not suggest those books in their answers. I suspect that you're referring to the usual RL book by Sutton and Barto. $\endgroup$
    – nbro
    Jul 14, 2021 at 19:42


You must log in to answer this question.