Questions
Let's try answering the following questions to assess our knowledge of what we learned in this chapter:
- Define the Bellman equation.
- What is the difference between the Bellman expectation and Bellman optimality equations?
- How do we derive the value function from the Q function?
- How do we derive the Q function from the value function?
- What are the steps involved in value iteration?
- What are the steps involved in policy iteration?
- How does policy iteration differ from value iteration?