CS 443 Reinforcement Learning (S23)

Introduction to reinforcement learning (RL).

Previous semesters (as CS 498): S21, F19.
Also see CS 542 for a more theoretical version of the course.

All slides, notes, and deadlines will be found on this website.


Date Lecture Comments
01/17 Introduction slides
01/19 MDP formulation slides
01/24 Value function note
01/26 Bellman equation  
01/31 Optimality  
02/02 Value Iteration blackboard
02/07 VI (cont) blackboard
02/09 Policy Iteration blackboard, HW1 due EOW
02/14 PI (cont), LP blackboard
02/16 Learning settings slides, blackboard
02/21 Value prediction slides, reading: Sec 3.1 of Szepesvári
02/23 TD blackboard, HW2 due EOW
02/28 Function approximation slides, blackboard, reading: Sec 3.2 of Szepesvári
03/02 Control slides
03/07 Off-policy learning  
03/09 In-class OH  
03/21 Importance sampling reference, slides, blackboard
03/23 IS HW3 due EOW
03/28 Policy gradient blackboard
03/30 PG slides
04/04 State abstraction slides
04/06 State abstraction ref, HW4 due EOW
04/11 In-class OH  
04/13 In-class OH  
04/18 Exam 1:50-3:25pm
04/20 Exploration slides
04/25 Partial observability slides
04/27 Bayesian RL slides
05/02 Imitation learning slides, 4 credit project due 05/07 EOD

Linear algebra, probability & statistics, and basic calculus. Experience with machine learning (e.g., CS 446) highly recommended.

Time & Location
Tue & Thu, 2-3:15pm. 1306 Everitt Lab.
In special circumstances we will meet over zoom instead (will be announced in advance); see Canvas announcement for the zoom link.

Lecture recording
Please see this channel on Mediaspace. You can subscribe to it to be automatically notified of new recordings.

We will not follow a specific textbook, but readings may be assigned based on the following textbooks whose pdfs are freely available online.

  • Reinforcement Learning: An Introduction, by Rich Sutton and Andrew Barto. (available online; also old version here)
  • Algorithms of Reinforcement Learning, by Csaba Szepesvári. (pdf available online)

Here. All announcements (including Assignments when they are created) will be made through Canvas, so make sure you can receive system notification emails from it.

TAs & Office Hours
Audrey Huang and Philip Amortila. OH: 1pm Friday.

Coursework & Grading
For 3 credit students: Your grade will consist of 2 components:

  • Homework (~70%): There will be roughly 5 homework assignments, including both written and coding assignments.
  • Final/Late Mid Exam (~30%): There will be a final exam (or a mid exam that is relatively late). Date TBA.

For 4 credit students: You will need to additionally work on a final project (20%; the points of other components will be reduced proportionally). You can either work on your own or work in a team of size 2. The project should be about reproducing the theoretical analysis or the empirical experiments of a published paper on RL; you do not need to reproduce the full paper and can be selective about which part you work on. You are expected to discuss with me the choice of topic in the middle of the semester. For those who want to work on theory, please refer to the CS542 site for the guidelines (though you are expected to spend less effort than the CS542 project) and the list of seed papers.

Academic Integrity
Jeff Erickson has a good page on this. TL;DR from him: “Be honest. Cite your sources. We mean it. If you need help, please ask.”

Late Policy
Late homework will not be accepted. Instead, your lowest homework score will be dropped. Additional late-exceptions will only be granted in a case-by-case manner when compelling reasons are presented (e.g., documented emergencies).

Please let me know as soon as possible if you need accommodations for disability.

Tentative List of Topics

  • MDP basics.
  • Planning: value iteration, policy iteration, and their analyses.
  • Model-based and value-based learning algorithms: certainty-equivalence, Q-learning, TD.
  • Policy gradient.
  • Importance sampling and off-policy evaluation.
  • State abstractions.
  • Partial observability.