Multi-Agent Reinforcement Learning: Chapter 5 First Steps for MARL in Games

This meeting we will begin Chapter 5 in Multi-Agent Reinforcement Learning: Foundations and Modern Approaches which introduces the first algorithms designed to compute game solutions. We will define convergence criteria for algorithms and then discuss the differences between central learning and independent learning. Central learning, in particular, has a clear connection to ordinary reinforcement learning, so reviewing the material and videos from the Sutton and Barto book would be helpful.

As usual you can find below links to the textbook, previous chapter notes, slides, and recordings of some of the previous meetings.

Meetup Links:
Recordings of Previous RL Meetings
Recordings of Previous MARL Meetings
Short RL Tutorials
My exercise solutions and chapter notes
Kickoff Slides which contain other links
MARL Kickoff Slides

MARL Links:
Multi-Agent Reinforcement Learning: Foundations and Modern Approaches
MARL Summer Course Videos
MARL Slides

Sutton and Barto Links:
Reinforcement Learning: An Introduction by Richard S. Sutton and Andrew G. Barto
Video lectures from a similar course