Emergent Heterogeneous Swarm Control Through Hebbian Learning

TL;DR

This paper presents Hebbian learning as a biologically inspired, local rule-based method for enabling heterogeneity and adaptive behavior in swarm robotics, reducing complexity and improving scalability.

Contribution

It introduces Hebbian learning as a novel, scalable approach for emergent heterogeneity in swarm control, bypassing the need for extensive prior knowledge or complex attribution.

Findings

Heterogeneity naturally emerges in swarm behavior.

Swarm capabilities significantly improve with Hebbian learning.

Evolution of Hebbian rules can replace reinforcement learning in benchmarks.

Abstract

In this paper, we introduce Hebbian learning as a novel method for swarm robotics, enabling the automatic emergence of heterogeneity. Hebbian learning presents a biologically inspired form of neural adaptation that solely relies on local information. By doing so, we resolve several major challenges for learning heterogeneous control: 1) Hebbian learning removes the complexity of attributing emergent phenomena to single agents through local learning rules, thus circumventing the micro-macro problem; 2) uniform Hebbian learning rules across all swarm members limit the number of parameters needed, mitigating the curse of dimensionality with scaling swarm sizes; and 3) evolving Hebbian learning rules based on swarm-level behaviour minimises the need for extensive prior knowledge typically required for optimising heterogeneous swarms. This work demonstrates that with Hebbian learning heterogeneity naturally emerges, resulting in swarm-level behavioural switching and in significantly improved swarm capabilities. It also demonstrates how the evolution of Hebbian learning rules can be a valid alternative to Multi Agent Reinforcement Learning in standard benchmarking tasks.