CS 4180/5180: Reinforcement Learning and Decision Making (Fall 2019)

Brief Course Description

This course will introduce the student to reinforcement learning. The bulk of what we will cover comes straight from the second edition of Sutton and Barto's book, Reinforcement Learning: An Introduction. However, we will also cover additional material drawn from the latest deep RL literature. The following list of topics is subject to revisions.

1. Problem formulation
• The reinforcement learning problem, anatomy of an RL agent
• Bandit problems
• Markov decision processes
2. Value function methods
• Monte Carlo
• Dynamic Programming
• Temporal Difference Learning
• Combining planning and learning
• Batch learning
3. Function Approximation
• Linear function approximation and LSTD
• Deep neural networks and DQN
• When does function approximation succeed and fail?
4. Policy Gradient Methods
• Policy gradient formulation
• REINFORCE
• Actor/critic methods
• DDPG, TRPO

The course schedule is subject to change. See the schedule tab above.

Textbook

Reinforcement Learning: An Introduction, 2nd Ed., Sutton and Barto

Prerequisites/Corequisites

1. Python 3.7, OpenAI Gym, PyTorch: You must be able to write code in Python 3.7 and to install OpenAI Gym and PyTorch. Ideally, you will do this on a Linux installation such as Ubuntu, but you may use other OSes at your own risk.
2. Probability: You should be comfortable with all of the concepts described here.
3. Calculus: You need to have taken a course in calculus that includes derivatives and integrals.
4. Algorithms: You need to have taken or be taking a course in algorithms such as CS 5800 or CS 7800. If you do not have this, but would still like to take the course, please contact the instructor.
5. Linear Algebra: You should be comfortable with all of the concepts described here.
6. GPU: It would help to have access to a cuda-enabled GPU (with the installed drivers), but it's not strictly necessary for the course.

Academic Integrity

Cheating and other acts of academic dishonesty will be referred to OSCCR (office of student conduct and conflict resolution) and the College of Computer Science. See this link.

Lateness Policy

Late assignments will be penalized by 10% for each day late. For example, if you turned in a perfect programming assignment two days late, you would receive an 80% instead of 100%.

Instruction Staff

Primary Instructor: Chris Amato ( c [dot] amato [at] neu [dot] edu )
Office hours: 3:15pm-4:45pm on Tuesdays in ISEC 522, or by Appt.

TA: Andrea Baisero: baisero [dot] a [at] husky [dot] neu [dot] edu
Office hours: Thursday 1:30pm-3pm, ISEC 505

TA: Behrooz Moradi Bajestani: moradibajestani [dot] b [at] husky [dot] neu [dot] edu
Office hours: Monday 12pm-1:30pm, ISEC 501