L-System Genetic Encoding for Scalable Neural Network Evolution: A Comparison with Direct Matrix Encoding

TL;DR

This study introduces L-System genetic encoding for neural networks, demonstrating significant improvements in performance, reliability, and generalization over traditional matrix encoding through extensive experiments.

Contribution

The paper presents a formal L-System based genetic encoding method for neural networks and compares it with matrix encoding, showing superior results across multiple metrics.

Findings

Lsys encoding achieved a 2.74x higher mean maximum food count than matrix encoding.

All Lsys populations successfully learned to navigate the environment, while half of the matrix populations failed.

Lsys populations demonstrated immediate robust generalization to new environments, outperforming matrix-encoded populations.

Abstract

An artificial world of barriers and plains scattered with food is used to test the feasibility of using genetic algorithms to optimize hebbian neural networks to perform on problems without apriori knowledge of the problem domain. A formal L-System based genetic alphabet for neural networks, titled Lsys, and a neural network genetic modeling tool titled Wp1hgn are introduced. Lsys and Matrix neural network topology genetic encoding methods are compared across 24 experimental runs. Lsys encoding achieved a mean maximum food count of 3802 +- 197 at generation 1000 across 8 runs with varied parameters, compared to 1388 +- 610 for Matrix encoding, a 2.74x performance advantage with an 8.5-fold improvement in consistency as measured by coefficient of variation (5.2% vs 44.0%). All 8 Lsys populations successfully learned to navigate the environment, while 4 of 8 Matrix populations failed to achieve competitive performance at any point during 1000 generations. When transferred to a novel maze environment, Lsys populations demonstrated immediate robust generalization, achieving a mean maximum food count of 2455 +- 176 compared to 422 +- 212 for Matrix populations, a 5.82x advantage that exceeded the training world performance gap. A MatrixLSG control condition, in which initial populations were generated using Lsys genotypes and then evolved using Matrix operators, demonstrated that the performance advantage of Lsys encoding derives primarily from the genetic algorithm operating on the compressed symbolic Lsys alphabet throughout evolution rather than from initial population structure. Lsys encoding is shown to provide faster convergence, higher peak performance, dramatically greater reliability, and superior generalization to novel environments compared to Matrix encoding across all experimental conditions tested.