Reinforcement Learning: Chapter 2 Multi-armed Bandits

Last meeting we concluded Chapter 1 and its exercises. This meeting we will begin Chapter 2 which covers multi-armed bandits and introduces action-value methods. Value functions are a critical component of most techniques in the book and this chapter introduces them in a setting which is simpler than the full reinforcement learning problem. We will likely make it through section 2.4 and the exercises therein.

As usual you can find below links to the textbook, previous chapter notes, slides, and recordings of some of the previous meetings.
Useful Links:
Reinforcement Learning: An Introduction by Richard S. Sutton and Andrew G. Barto
Recordings of Previous Meetings
Short RL Tutorials
My exercise solutions and chapter notes
Kickoff Slides which contain other links
Video lectures from a similar course