Lecture 4 Flashcards
1
Q
What is the notation with an infinite horizon decision problem where you discount the costs?
A
2
Q
What is the theoretical improvement step of the discounted cost critereon?
A
3
Q
What is the actual application of the improvement step?
A
4
Q
What is the Policy Iteration Algorithm for Discounted MDP?
A
5
Q
What is the theoretical improvement step for policy iteration for the long-run average cost critereon?
A
6
Q
How to apply the improvement step for policy iteration for the long-run average cost critereon?
A
7
Q
What is the algorithm for policy iteration for the long-run average cost critereon?
A
8
Q
What are the optimality equations for the long-run average cost critereon?
A
