Mean Field Games Flock! The Reinforcement Learning Way

Understand

We present a method enabling a large number of agents to learn how to flock, which is a natural behavior observed in large populations of animals.

• This problem has drawn a lot of interest but requires many structural assumptions and is tractable only in small dimensions.
• We phrase this problem as a Mean Field Game (MFG), where each individual chooses its acceleration depending on the population behavior.
• Combining Deep Reinforcement Learning (RL) and Normalizing Flows (NF), we obtain a tractable solution requiring only very weak assumptions.