Rubric

Keep in mind that 2 students have already been assessed using this rubric. Changing it will affect their evaluations.
Project 6: CS4013 Rubric
Project 6: CS4013 Rubric
Criteria Ratings Pts
Graphics
threshold: pts
10 pts Full Marks correctly drawing graphics (or using printouts) that enable you to debug your learning and that help us to grade it.
7 pts Minor bugs
3 pts Major bugs
0 pts No Marks
pts
10 pts
--
Good coding practices
threshold: pts
10 pts Full Marks well commented code, descriptive variables names or making good use of classes and methods
5 pts partial credit partially commented code, semi-descriptive variable names, or partial use of classes and methods
0 pts No Marks
pts
10 pts
--
Writeup: Learning curve and analysis
threshold: pts
20 pts Full Marks demonstrating learning using a learning curve (in the writeup).  For full credit, make sure you explain why it is learning or not learning (if it isn't learning, you will not lose your points if you can explain WHY it is not learning)
10 pts Learning not demonstrated and no analysis of why it isn't learning
0 pts No Marks
pts
20 pts
--
Writeup: learning description
threshold: pts
10 pts Full Marks describing your RL approach including your state space and reward function in a paragraph or two
5 pts Description lacking
0 pts No Marks
pts
10 pts
--
RL method
threshold: pts
20 pts Full Marks correctly implemented the RL method that you proposed and got feedback on (if you were told to choose a different method, you need to implement the method you were told to adjust to).  A correct learner uses learning in a way to improve performance and learning will be demonstrated in the writeup (though the curve is graded separately) using a learning curve.  Learning code should be well documented to receive full credit.
15 pts minor mistakes
10 pts documentation missing or several mistakes
5 pts major errors
0 pts No Marks
pts
20 pts
--
RL state space
threshold: pts
10 pts Full Marks state space representation is appropriate to the task being solved and is correctly implemented
5 pts bugs
0 pts No Marks
pts
10 pts
--
RL reward
threshold: pts
10 pts Full Marks reward function appropriate to the task being solved and is correctly implemented
5 pts bugs
0 pts No Marks
pts
10 pts
--