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

by   Aadesh Neupane, et al.

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.


page 1

page 2

page 3

page 4


Understandable Controller Extraction from Video Observations of Swarms

Swarm behavior emerges from the local interaction of agents and their en...

Mimicking Evolution with Reinforcement Learning

Evolution gave rise to human and animal intelligence here on Earth. We a...

Leveraging Human Feedback to Evolve and Discover Novel Emergent Behaviors in Robot Swarms

Robot swarms often exhibit emergent behaviors that are fascinating to ob...

How to Make Swarms Open-Ended? Evolving Collective Intelligence Through a Constricted Exploration of Adjacent Possibles

We propose an approach of open-ended evolution via the simulation of swa...

Optimisation of Air-Ground Swarm Teaming for Target Search, using Differential Evolution

This paper presents a swarm teaming perspective that enhances the scope ...

Search and Rescue in a Maze-like Environment with Ant and Dijkstra Algorithms

With the growing reliability of modern Ad Hoc Networks, it is encouragin...

Please sign up or login with your details

Forgot password? Click here to reset