Problem Set 6

Exercises are taken from the textbook chapters. Maximum score for this problem set is 19 points and the due date is Monday, November 30th, 2020 (11:59PM Eastern Time)

• Exercise 9.1: (a) 2 points, (b) 2 points, (c) 4 points, (d) 1 points.
• Exercise 9.2: (a) 2 points, (b) 2 points. (c) 4 points.
• Project Update 2: A short (max 500 words) report where you describe how you have progressed so far in the project. See also the class website. If you have a specific section you are stuck on, be sure to note roadblocks so we can give you advice. By uploading your project proposal to Gradescope you will get one point. This is just to ensure that the upload has been completed successfully: the project update is mandatory.
• Survey: 1 point. After submitting the survey, write the keyword at the end of your written submission. The survey is anonymous!

You will have to make three submissions for this problem set:

• Problem Set 6, Written Submission. A pdf of your answers to 9.1(c). This can be either LaTeX, Word, or hand-written (in the latter case, be sure it is legible!). Please include the survey keyword in the end of your written submission.
• Problem Set 6, Notebook Submission. The final versions of your notebooks stochastic_optimization.ipynb, policy_gradient.ipynb (downloaded from Colab). Please double check that the notebook you are submitting has exactly this name.
• Project Progress Update 2. The pdf of your project update. This can be either LaTeX (preferred) or Word. The project update cannot be handwritten.

For the notebook submission, Gradescope will give you a grade within approximately 60 seconds. You can resubmit as many times as you like before the deadline.

Finally, we have a small survey that you can take for an extra point! After you take the survey, you will be given a code. Submit this code to Gradescope's written submission section!