This workshop will give participants the opportunity to learn about the theory and practice of multi-agent reinforcement learning (MARL). MARL extends the decision-making capabilities of single-agent reinforcement learning (RL) to the setting of distributed decision-making problems. In MARL, multiple agents are trained to act as individual decision-makers of some larger system, while learning to work as a team. MARL can be applied in situations where the problem becomes exponentially more difficult to solve as it scales. For example, in managing a fleet of autonomous vehicles for a growing population, the number of navigation decisions that must be made at any given time scales exponentially with the size of the fleet. This quickly becomes intractable for single-agent approaches whereas for MARL, is an opportunity to shine. In this workshop, we will show participants how to use Mava, a research framework for MARL to build a multi-agent learning system for a real-world use case. We will provide the necessary guidance, tools and background to understand the key concepts behind MARL, how to use Mava building blocks to build systems and how to train a system from scratch. 

At the end of the workshop, participants should have a good understanding of key concepts in MARL, potential use-cases and how the computational framework of MARL might differ from other approaches to solving complex problems. 
On the practical side, participants: 

• Should have the knowledge to be able to frame a real-world problem as a MARL problem and know when this might, or might not, be the appropriate view.
• Are able to use components and modules from the Mava framework to build a multi-agent system and train this system on a particular example use case.

• Participants should be comfortable with programming in Python. 
• Have a basic understanding of key concepts in machine learning and in particular, reinforcement learning. 
• No prior knowledge of multi-agent reinforcement learning is expected or required.