Multi-Agent Reinforcement Learning: Chapter 4 Solution Concepts for Games

This meeting will cover material from Chapter 4 of Multi-Agent Reinforcement Learning: Foundations and Modern Approaches. We will cover normal form games and types of solutions that exist such as minimax and Nash equilibrium. Initially we will consider two player zero sum games with only two actions and slowly expand the complexity of the reward function and dimensionality. For many game types, the equilibrium solutions are not unique, so the challenge becomes selecting which one is relevant to us and how to calculate it.

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