Multi Agent Reinforcement Learning: AlphaStar Introduction

This meeting will continue with section Chapter 9.9.3 of Multi-Agent Reinforcement Learning: Foundations and Modern Approaches which discusses the DeepMind agent AlphaStar and its league training approach to developing robust strategies. We have a general overview of the AlphaStar project and look at the initial test results in some detail. We will begin with the first blog post published by DeepMind on the topic and the associated live demonstration. Eventually we will also look at the associated blog post and Nature paper that were published later that year.

You can find below links to notes and recordings of 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