Skip to main content

Class Logistics

Course Overview

Decision Making has made massive strides over the past decade, from monumental achievements in gaming(Atari and Go) to the seamless control of robots in diverse applications. This is a graduate-level course on Decision Making, with a dedicated focus on practical applications and recent research breakthroughs. Students will be introduced to a broad set of topics, covering essential formalisms, latest concepts in Imitation Learning, the nuances of Behavior Cloning, and the powerful realm of Reinforcement Learning (RL). Applications across industries such as gaming, robotics, and industry will be discussed to offer a holistic perspective of the impact of decision-making in various domains. This course will involve several coding home-works where you will implement various algorithms and a final project.

Target Audience

This course is aimed at MSc and PhD level students in computer science / data science.


CS / Data Science Students

This is NOT a basic course in reinforcement learning, deep learning or AI. If you are unsure about whether you are ready to take the class, go through Assignment 0 to test yourself.

  • Graduate level knowledge of machine learning, computer vision, and deep learning is assumed.
  • Proficiency in Python and PyTorch is assumed, and will be necessary to complete the assignments.

For non-DS/CS Students

Please contact Rosemary Amico (

Logistical Overview


  • 4:55pm-6:55pm on Fridays.
  • Lectures wil be held in person.
  • The class will be recorded, we will post the link to the recorded lectures to the class campuswire.
  • Please add the (Class calendar) to your calendar to keep track of class events (lecture, office hours, recitation, etc.).

Grading and Assignments

  • Assignments (40%) + Final Project (50%) + Class Participation (10%)
  • There will be four assignments through the semester.
  • Three late days are provided for late submission. No submissions will be accepted after the late days are used by the student.
  • Assignments will use Python 3 and PyTorch; we will provide you a conda environment to install all dependencies.
  • We strongly recommended using Python for the project as well.

Final Project

  • Project proposals (1 page) will be due on 2/23.
  • Maximum (and recommended) team size is 2.
  • Final presentations of all projects will take place on 5/3/2024.

Course Textbook

We highly recommend the following e-book: Sutton and Barto. Reinforcement Learning. Reading materials for each class is posted in the schedule.

Course Staff

Office Hours

  • Lerrel: TBD
  • Siddhant: Wednesday, 3pm - 4pm


  • A student in this course is expected to act professionally. Please also follow the GSAS regulations on academic integrity found here:
  • Academic accommodations are available for students with disabilities. Please contact the Moses Center for Students with Disabilities (212-998-4980 or for further information. Students who are requesting academic accommodations are advised to reach out to the Moses Center as early as possible in the semester for assistance.