CSE571: MDP homework and project (to be continued)

["Tuan A. Nguyen" <tanguye1@asu.edu>]

Hi all:

Please find here the homework and project for the MDP part of the course. We will also post one more exercise for the finite-horizon MDP, so stay tuned.

---

Part 1:

Do the exercises 17.4, 17.8, 17.9 and 17.10 in the AIMA textbook (see the attachment). 

Part 2: Implement the following algorithms: value iteration, policy iteration and modified policy iteration. Test your code with the world in Figure 17.1 and observe the performance of those algorithms with different starting states. Use your code to verify your answer for exercise 17.8. You will need to submit your code and report on what you observe through these experiments.

Note that you will use your implementation for Reinforcement Learning project, so make it as flexible as you can. No constraints on languages.

Due date: 09/19 (this can be changed depending on how slow the lecture is going in class)

---

Please let me know if you have any questions.

Tuan

Attachment: MDP Homeworks.pdf
Description: Adobe PDF document