CS 4789/5789: Introduction to Reinforcement Learning

Modern Artificial Intelligent (AI) systems often need the ability to make sequential decisions in an unknown, uncertain, possibly hostile environment, by actively interacting with the environment to collect relevant data. Reinforcement Learning (RL) is a general framework that can capture the interactive learning setting and has been used to design intelligent agents that achieve super-human level performances on challenging tasks such as Go, computer games, and robotics manipulation.

This course focuses on basics of Reinforcement Learning. The four main parts of the course are (1) basics of Markov Decision Process, (2) Planning and Control in MDP, (3) Learning in MDPs, and (4) imitation learning.

After taking this course, students will be able to understand classic RL algorithms and their analysis.

All lectures will be math heavy. We will go through algorithms and their analysis.


Instructors: Wen Sun (Cornell)

TAs: Wen-Ding Li, Hadi Alzayer

Lecture time: Tuesday/Thursday 9:40am - 10:55am ET

Instructor office hours: Tuesday and Thursday after class (10:55am-11:30am)

TAs office hours: Wen-Ding: Friday 3-4pm, Hadi: Wednesday 2:30-3:30pm

Contact: cornellcs4789@gmail.com

Please communicate to the instructors and TA only through this account. Emails not sent to this list, with regards to the course, will not be responded to in a timely manner.

Recorded Lectures

We are gradually releasing recorded lectures here


Since lectures are math heavy and we will focus on algorithm design and analysis, we require students to have strong Machine Learning background (e.g., CS 4780). Students should be comfortable about basics of probability and linear algebra.

Since HWs contain programming problems, we expect students are comfortable about programming. We will use Python as the programming language in ALL HWs.

Grading Policies

Assignments 70% (HW0: 10%, HW1-HW3: 20% each); Final 30%; Attendance bonus 5%

All homeworks contain both math and programming (we use Python and OpenAI Gym).

Final exam only contains math

Homework Rules: Homework must be done individually: each student must understand, write, and hand in their own submission. Solutions need to be typed (we encourage you to use Latex).

It is acceptable for students to discuss problems with each other; it is not acceptable for students to look at another students written answers. You must also indicate on each homework with whom you collaborated with and what online resources you used.

Late days: Homeworks must be submitted by the posted due date. You are allowed up to 6 total LATE DAYs for the homeworks throughout the entire semester. These will be automatically deducted if your assignment is late. For example, any day in which an assignment is late by up to 24 hours, then one late day will be used (up to two late days). After your late days are used up, late penalties will be applied: any assignment turned in late will incur a reduction in score by 33% for each late day, so if an assignment is up to 24 hours late, it incurs a penalty of 33%. Else if it is up to 48 hours late, it incurs a penalty of 66%. And any longer, it will receive no credit. We will track all your late days and any deductions will be applied in computing the final grades. If you are unable to turn in HWs on time, aside from permitted days, then do not enroll in the course.

Diversity and Inclusiveness

While many academic disciplines have historically been dominated by one cross section of society, the study of and participation in STEM disciplines is a joy that the instructors hope that everyone can pursue, regardless of their socio-economic background, race, gender, etc. We encourage students to both be mindful of these issues, and, in good faith, try to take steps to fix them. You are the next generation here.

You should expect and demand to be treated by your classmates and the course staff with respect. You belong here, and we are here to help you learn and enjoy this course. If any incident occurs that challenges this commitment to a supportive and inclusive environment, please let the instructors know so that the issue can be addressed. We are personally committed to this, and subscribe to the Computer Science Department Values of Inclusion.

Honor Code

  • Collaborations only where explicitly allowed
  • Do not use of forums like Course Hero, Chegg;
  • Whatever materials you use for your HWs, properly cite the references; If you are unclear about whether some online material can be used, ask instructors and TAs first
  • No sharing of your solutions within or outside class at any time
  • We will be extremely serious about academic integrity. The above is not an exhaustive list, and in general any Cornell and common sense rules about academic integrity apply. If it is not something we explicitly allowed, ask us whether it is OK before you do it.

    Cornell University Code of Academic Integrity, CS Department Code of Academic Integrity.

    Course Notes

    The course will sometimes use working draft of the book "Reinforcement Learning Theory and Algorithms", available here.

    Note that this is an extremely advanced RL theory book. A lot of the materials in the book are out of the scope of this class. Thus we will pick very specific sections for you to read.

    If you find typos or errors, please let us know. We would appreciate it!

    You can also self-study the classic book "Reinforcement Learning: An Introduction", available here

    Schedule (tentative)

    Lecture Reading Slides/HW
    02/9/21 Fundamentals: Markov Decision Processes AJKS: 1.1.1, 1.1.2 Slides, Annotated Slides
    02/11/21 Fundamentals: Markov Decision Processes (Continue) AJKS: 1.1.1, 1.1.2 Slides, Annotated Slides
    02/16/21 Fundamentals: Policy Evaluation AJKS: 1.1.1, 1.1.2 Slides, Annotated Slides
    02/18/21 Fundamentals: Value Iteration AJKS: 1.4.1 Slides, Annotated Slides
    02/23/21 Fundamentals: Policy Iteration AJKS: 1.4.2 Slides, Annotated Slides
    02/25/21 Control: Linear Quadratic Regulator (LQRs) AJKS: 13.1 Slides, Annotated Slides
    03/2/21 Control: Optimal Control in LQRs AJKS: 13.2 Slides, Annotated Slides, HW0 Due
    03/4/21 Control: Control for Nonlinear systems (Iterative LQR) Note on iLQR Slides, Annotated Slides
    03/9/21 No Class
    03/11/21 Learning: Model-baesd RL w/ Generative Model Note on Simulation Lemma Slides, Annotated Slides
    03/16/21 Learning: Supervised Learning & Approximate Policy Iteration AJKS: 4.1 Slides, Annotated Slides
    03/18/21 Learning: Approximate Policy Iteration & Performance Difference Lemma Note on PDL Slides, Annotated Slides, HW 1 Due
    03/23/21 Learning: Conservative Policy Iteration AJKS: 12.1 (up to proof of Theorem 12.2) Slides, Annotated Slides
    03/25/21 Learning: (Stochastic) Gradient Descent & Policy Gradient AJKS: 9.1 Slides, Annotated Slides
    03/30/21 Learning: PG Continue Slides, Annotated Slides
    04/01/21 Learning: Trust Region and Natural PG AJKS: 12.2 Slides, Annotated Slides
    04/6/21 Learning : NPG Continue and Review Slides, Annotated Slides
    04/8/21 Imitation Learning: Behavior Cloning Slides, Annotated Slides
    04/13/21 Imitation Learning: Interactive Learning w/ DAgger Slides
    04/15/21 Imitation Learning: DAgger (continue) Slides, Annotated Slides, HW 2 due (April 16th)
    04/20/21 Imitation Learning: Maximum Entropy Inverse RL Slides, Annotated Slides
    04/22/21 Imitation Learning: MaxEnt-IRL (Continued) Note on MaxEnt RL and Soft VI Slides, Annotated Slides
    04/27/21 Exploration: Exploration in RL and Multi-armed Bandits Note on MAB Slides, Annotated Slides
    04/29/21 Exploration: Multi-armed Bandits (Continue) Note on UCB Slides, Annotated Slides
    05/4/21 Exploration: Contextual Bandit Slides, Annotated Slides
    05/6/21 Case Study: AlphaGo AlphaGo Paper link Slides, Annotated Slides
    05/11/21 Review Slides, Annotated Slides, HW 3 Due
    05/13/21 No class
    Final Week Final Exam (May 21st 1:30pm ET)