MARL Chapter 9.4: Multi-Agent Policy Gradient Algorithms

This meeting will continue the material from Chapter 9 in Multi-Agent Reinforcement Learning: Foundations and Modern Approaches. Previously we covered the most basic independent learning algorithms that reduce the problem to a single agent RL model from the perspective of each agent. This section will extend these techniques to incorporate some information flow between the agents through a centralized critic and equilibrium estimation methods.

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 for Sutton-Barto
My MARL repository
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