Theory of reinforcement learning (RL), with a focus on sample complexity analyses.
Previous semesters: F21; as CS598: F20, S19, F18
| Date | Lecture | Comments |
|---|---|---|
| 08/24 | Overview, logistics, and MDP basics | slides |
| 08/26 | MDP basics | note1, homework 0 |
| 08/31 | Value iteration | |
| 09/02 | VI | HW1 available on Canvas |
| 09/07 | Watch F21 video on Policy Iteration | Instructor travelling |
| 09/09 | Watch F21 video on Linear programming | Instructor travelling |
| 09/14 | Review of previous lectures & concentration ineq | note2 |
| 09/16 | Certainty-equivalence | note3 (updated 09/16: alt. proof of simulaiton lemma) |
| 09/21 | CE | |
| 09/23 | Abstraction | note4, slides |
| 09/28 | FQI/E | slides (updated: 10/05) |
| 09/30 | FQI/E | note5 (updated: 10/06), Akshay’s note |
| 10/05 | FQE proof | |
| 10/07 | FQI proof, pessimism | |
| 10/12 | Importance sampling | note6 |
| 10/14 | IS, PG | |
| 10/19 | Marginaized IS | Ref: MWL/MQL, interval |
| 10/21 | Exploration (tabular) | note7 |
| 10/26 | Rmax proof | |
| 11/02 | Bellman rank | slides |
| 11/04 | OLIVE | blackboard |
| 11/09 | Martingale concentration, ridge regression | note8 |
| 11/11 | Elliptical potential and Covering | |
| 11/16 | Regret of UCB-LSVI | |
| 11/18 | BVFT | slides |
| 11/30 | Partial observability | slides |
| 12/02 | PSRs |
Time & Location
Wed & Fri, 2-3:15pm. Location has changed! Rm 2310 Rm 1302, Everitt Laboratory.
Recording
Lectures will be recorded and made available on Mediaspace (log in required). You can subscribe to the channel to be alerted about new recordings.
Online Platform
Canvas will be used as the main platform for announcements, discussions, and homework submissions. It is important that you join the Canvas space for this course and turn on notifications to receive announcements in a timely manner. If you enroll in the course after 08/20 or are auditing, please contact the TA (Jinglin Chen, jinglinc@illinois.edu) to add you to Canvas.
TA
Jinglin Chen, Tengyang Xie.
Office Hours
I will stay till 4pm for questions after each lecture (may leave early if no one is in the classroom). Additional TA OHs may be added in an on-demand manner.
Prerequisites
Linear algebra, probability & statistics, and basic calculus. Experience with machine learning (e.g., CS 446), and preferably reinforcement learning. It is also recommended that the students are familiar with stochastic processes and numerical analysis.
Coursework & Grading
The main assignment will be a course project that involves literature review, reproduction of theoretical analyses in existing work, and original research (see details below). No exams. Grades decomposition: tentatively 40% homework and 60% project; subject to +-10% changes depending on the actual number of graded homework assignments (expected: 3; there will be 1-2 separate assignments that are not graded).
Statement on CS CARES and CS Values and Code of Conduct
All members of the Illinois Computer Science department - faculty, staff, and students - are expected to adhere to the CS Values and Code of Conduct. The CS CARES Committee is available to serve as a resource to help people who are concerned about or experience a potential violation of the Code. If you experience such issues, please contact the CS CARES Committee. The instructors of this course are also available for issues related to this class.
Topics Covered in Lectures
Course Project
You will work individually. You can choose one of the following three types of projects:
Reproduce the proofs of existing paper(s). You must fully understand the proofs and rewrite them in your own words. Sometimes a paper considers a relatively general setting and the analysis can be quite complicated. In this case you should aim at scrutinizing the results and presenting them in the cleanest possible way. Ask yourself: What’s the most essential part of the analysis? Can you introduce simplification assumptions to simplify the proofs sigificantly without trivializing the results?
Novel research Pick a new research topic and work on it. Be sure to discuss with me before you settle on the topic. The project must contain a significant theoretical component.
Something between 1 & 2 I would encourage most of you to start in this category. The idea is to reproduce the proofs of existing results and see if you can extend the analysis to a more challenging and/or interesting setting. This way, even if you do not get the new results before the end of semester, your project will just fall back to category 1.
See the link at the top of this page for potential topics. You are expected to submit a short project proposal in the middle of the semester. The proposal should consist of a short paragraph describing your project topic, the papers you plan to work on, and the original research question (if applicable).
Resources
Useful inequalities cheat sheet (by László Kozma)
Concentration of measure (by John Lafferty, Han Liu, and Larry Wasserman)
We will not follow a specific textbook, but here are some good books that you can consult:
Alekh Agarwal, Sham Kakade, Wen Sun, and I also have a draft monograph which contained some of the lecture notes from this course.
There are also many related courses whose material is available online. Here is an incomplete list (not in any particular order; list from 2019 and has not been updated since then):