Reinforcement Learning / Fall 2022
New Lecture is up: Offline Reinforcement Learning
Our course project presentation is scheduled on December 12, Monday, 10:30am-1:00pm EST, at Rice 340. Each team is required to give the presentation in person. And we will provide light refreshment to help you enjoy the presentations and discussions.
New Lecture is up: Deep Reinforcement Learning [slides]
New Lecture is up: Approximation Methods [slides]
New Assignment released: [MP #3 - Policy Gradient method]
New Lecture is up: Policy Gradient Methods [slides]
New Assignment released: [ICLR2023 Review Assignment]
This is an undergraduate-level course on reinforcement learning. We will discuss the foundations in reinforcement learning, starting from multi-armed bandits, to Markov Decision Process, planning, on-policy and off-policy learning, and its recent development under the context of deep learning.
Register to our Piazza course forum to get course notifications via email.
Time: Tuesday/Thursday, 9:30am-10:45am, both in-person in Thornton Hall E303 and online via Zoom. You can find our Zoom meeting links in collab.
Office Hours: You can request the Zoom links for our office hours via email, but please make an appointment beforehand (at least two hours in advance). You can also request in-person meetings if you feel that would make our discussions more effective.
1. Instructor, Tuesday/Thursday, 4pm-5pm;
2. TA, Wednesday/Friday, 2pm-3pm.