Evolving Neural Networks through Augmenting Topologies

Abstract¶

An important question in neuroevolution is how to gain an advantage from evolving neural network topologies along with weights. We present a method, NeuroEvolution of Augmenting Topologies (NEAT) that outperforms the best fixed-topology method on a challenging benchmark reinforcement learning task. We claim that the increased efficiency is due to (1) employing a principled method of crossover of different topologies, (2) protecting structural innovation using speciation, and (3) incrementally growing from minimal structure. We test this claim through a series of ablation studies that demonstrate that each component is necessary to the system as a whole and to each other. What results is significantly faster learning. NEAT is also an important contribution to GAs because it shows how it is possible for evolution to both optimize and complexify solutions simultaneously, offering the possibility of evolving increasingly complex solutions over generations, and strengthening the analogy with biological evolution.

Summary¶

Introduces NEAT, which evolves both neural-network weights and topology by protecting innovations through speciation and growing complexity incrementally. It is a foundational neuroevolution algorithm and a clear example of evolution optimizing structure, not just parameters.

Links¶

Tags¶

Similar Papers¶