June–August 2025 Session Topic: Reinforcement Learning (RL) and multi-agent extensions
In this reading group, we will primarily read the Reinforcement Learning: An Introduction by Richard Sutton and Andrew Barto. After getting familiar with RL basics in first few weeks, we shall move to study some classic/frontier multi-agent RL literatures (i.e. a game theory based perspective). More papers as resources will be posted later under `Supplemtary Materials` below.
This reading group is online (on Zoom) for summer 2025 – we meet weekly, please check timetable below for exact meeting times (could vary by week)
Please check this page regularly for the most up-to-date arrangement.
If it is your first time attending a reading group, you might find the reading group tips by Lester Mackey and Percy Liang helpful.
Every time we will have one person (presenter) present the main contents and another person (discussant) raise questions and lead the discussion.
As a presenter: you should have an in-depth reading and develop a solid understanding of all the details in the assigned topic. You should prepare well, and make sure you deliver a logically clear and technically accessible presentation. In short, it is your job to have everyone in the meeting understand the main ideas of the reading.
As a discussant: you should be more familiar with the content than if you were simply in the group. You don’t need to know everything. You can pause the presentation, ask questions (to the presenter or to the audience), and facilitate discussions. It is your job to help the presenter to have everyone (yourself included!) in the meeting understand the main ideas of the reading and have learned something.
Before each session, although not compulsory, I would recommend the following amount of time spent on reading: