Emergent Escape-based Flocking Behavior using Multi-Agent Reinforcement Learning

TL;DR

This paper introduces SELFish, a multi-agent reinforcement learning approach where autonomous agents develop flocking behavior to evade predators, revealing emergent collective strategies in a simulated environment.

Contribution

The paper presents a novel multi-agent reinforcement learning framework that results in emergent flocking behavior similar to natural swarms, with insights into predator-prey dynamics.

Findings

Agents develop flocking behavior similar to Boids.

Predator distraction influences swarm formation.

Emergent strategies improve survival in simulated environment.

Abstract

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.