HW4: TD Learning, Q-Learning, & Policy Gradient
- Due Mar 16, 2018 by 11:59pm
- Points 100
- Submitting a file upload
- File Types pdf
- Available Feb 28, 2018 at 1pm - Mar 16, 2018 at 11:59pm
Rubric
Find RubricKeep in mind that 63 students have already been assessed using this rubric. Changing it will affect their evaluations.
| Criteria | Ratings | Pts | |||
|---|---|---|---|---|---|
|
Direct estimation /evaluation
threshold:
pts
|
|
pts
--
|
|||
|
Transition probabilities
threshold:
pts
|
|
pts
--
|
|||
|
Q-learning
threshold:
pts
|
|
pts
--
|
|||
|
Policy gradient
threshold:
pts
|
|
pts
--
|
|||
|
Total Points:
100
out of 100
|
|||||