Assignment #5 - MDP and Reinfocement learning
Due Date: 1398/3/13 23:59
Download [problems] [attachment] [solutions]
Late Policy
- You have free 8 late days.
- You can use late days for assignments. A late day extends the deadline 24 hours.
- Once you have used all 8 late days, the penalty is 10% for each additional late day.
In this assignment you will experiment with simple RL agents.
Setup
Note: This assignment is using Python 2.7, please make sure you have it installed on your system. This assignment also need python Tkinter package, it is included in every python installation by default. however if you get error on Tkinter installation try this:
sudo apt install python-tk
Follow the pdf document for the rest of the assignment.
Submission for Theory Questions
After you’re ready to submit your work, Please follow these steps:
- Scan your written answers.
- Upload it to Quera Class
Submission for Practical Questions
- Make sure your current directory is assignment folder. Run the following command and Substitute <student_id> with your student ID (e.x: 95529876)
python make_submission.py <student_id>
- Grab
asg05_<student_id>.zip
, and Upload Zip file in Quera Class.
If you don’t follow the protocol, Unfortunately we are not able to get your submission thus you will NOT earn any scores.