Multi-Agent Reinforcement Learning Chapter 4: Nash Equilibrium and Welfare/Fairness Criteria

Live recording of online meeting reviewing material from "Multi-Agent Reinforcement Learning: Foundations and Modern Approaches" by Stefano V. Albrecht, Filippos Christianos, Lukas Schäfer. In this meeting we analyze general sum games and equilibrium solutions such as the Nash equilibrium. We solve the 2x2 game exactly and note some of the shortcomings of equilibrium solutions including non-uniqueness. Finally, we address methods of filtering solutions by criteria that maximize total reward across the agents or evenly distributed rewards. A few example games are used to illustrate what types of solutions exist and are desirable including: chicken, battle of the sexes, prisoner's dilemma, and stag-hunt.

The textbook website contains materials provided by the authors including a pdf of the text, slides, and a github repository with code.

MARL textbook website: https://www.marl-book.com/
MARL kickoff slides: https://docs.google.com/presentation/...

This online meeting is hosted through https://www.meetup.com/boulderdatasci... and https://www.meetup.com/silicon-valley...

For background material covering traditional reinforcement learning see the following playlist:    • Reinforcement Learning Tutorial Meetings  

Notes and interactive tools seen in those video use the Julia Language (https://julialang.org/) and the package Pluto.jl (https://plutojl.org/).

Previous meetings have covered the textbook "Reinforcement Learning: An Introduction" by Richard S. Sutton and Andrew G. Barto and the following links relate to that material and my notes/code based on it.

Sutton and Barto Textbook: http://incompleteideas.net/book/the-b...
HTML Notes: https://jekyllstein.github.io/Reinfor...
GitHub Repository: https://github.com/jekyllstein/Reinfo...

#reinforcementlearning #education #multiplayergames