Efficiently Evolving Swarm Behaviors Using Grammatical Evolution With PPA-style Behavior Trees

TL;DR

This paper presents a systematic method combining PPA-style Behavior Trees with Grammatical Evolution to efficiently evolve swarm behaviors, significantly improving success rates over previous approaches.

Contribution

It introduces a novel approach that replaces ad hoc reward functions with PPA-based checks, enabling a common grammar to adapt to multiple tasks using environmental cues.

Findings

75% success rate in learning trials for foraging and nest maintenance

Eight-fold improvement over prior work in swarm behavior evolution

Agents quickly adapt to new contexts despite poor static performance

Abstract

Evolving swarm behaviors with artificial agents is computationally expensive and challenging. Because reward structures are often sparse in swarm problems, only a few simulations among hundreds evolve successful swarm behaviors. Additionally, swarm evolutionary algorithms typically rely on ad hoc fitness structures, and novel fitness functions need to be designed for each swarm task. This paper evolves swarm behaviors by systematically combining Postcondition-Precondition-Action (PPA) canonical Behavior Trees (BT) with a Grammatical Evolution. The PPA structure replaces ad hoc reward structures with systematic postcondition checks, which allows a common grammar to learn solutions to different tasks using only environmental cues and BT feedback. The static performance of learned behaviors is poor because no agent learns all necessary subtasks, but performance while evolving is excellent because agents can quickly change behaviors in new contexts. The evolving algorithm succeeded in 75\% of learning trials for both foraging and nest maintenance tasks, an eight-fold improvement over prior work.