Read the following materials this week:

• Chapter 17 - Markov Decision Processes (MDPs)

  • Section 17.1 - Study this material on MDPs and policies.
  • Sections 17.2-3 - Study the material on value iteration (Section 17.2), skimming through the convergence material (Section 17.2.3) and policy iteration (Section 17.3).

  We’ll skip the material on POMDPs (Section 17.4) and game theory (Sections 17.5-6).

• Chapter 21 - Reinforcement learning

  • Section 21.1 - Study this material on reinforcement learning.
  • Section 21.2 - Study this material on passive reinforcement learning, particularly on the ADP and TD algorithms.

  We’ll skip the remainder of the material in this chapter.