Emergent Escape-based Flocking Behavior using Multi-Agent Reinforcement Learning
This addresses swarm behavior modeling for robotics or simulations, but it is incremental as it builds on existing Boids and reinforcement learning methods.
The paper tackled the problem of simulating flocking behavior in multi-agent systems by training self-interested agents with reinforcement learning to avoid a predator, resulting in emergent flocking similar to Boids simulations.
In nature, flocking or swarm behavior is observed in many species as it has beneficial properties like reducing the probability of being caught by a predator. In this paper, we propose SELFish (Swarm Emergent Learning Fish), an approach with multiple autonomous agents which can freely move in a continuous space with the objective to avoid being caught by a present predator. The predator has the property that it might get distracted by multiple possible preys in its vicinity. We show that this property in interaction with self-interested agents which are trained with reinforcement learning to solely survive as long as possible leads to flocking behavior similar to Boids, a common simulation for flocking behavior. Furthermore we present interesting insights in the swarming behavior and in the process of agents being caught in our modeled environment.