L8 Study Instructions

We watch DS8. This lecture focuses on integrating learning and planning.

DS8 Slides Link Links to an external site.

DS8 Video Link Links to an external site.
Tinkering Notebook for Lecture 8 Download Tinkering Notebook for Lecture 8

Notebook updated on 2020/05/27: visited_states variable is processed so that it only contains unique elements, see #tag_unique in the notebook.  Thanks to Gustav Björdal for pointing out this issue.

Reading Instructions:

We read Chapter 8.   For the Go example, you can also read Section 16.6 as optional reading.

Study Questions:

L8 Q1: Work on Exercise 8.1.

L8 Q2: Consider Exercise 8.4. Try to explain what will happen without carrying out the implementation.

L8 Q3: Work on Exercise 8.5.

L8 Q4:  Examine Figure 8.7.  What kind of guidelines do the plots suggest for RL algorithm development?

L8 Q5:  Examine Figure 8.8. What kind of guidelines do the plots suggest for RL algorithm development?