Hybrid Self-Attention NEAT: A novel evolutionary approach to improve the NEAT algorithm

TL;DR

This paper introduces Hybrid Self-Attention NEAT, an evolutionary approach that enhances NEAT's ability to handle high-dimensional inputs by integrating self-attention and hybrid evolution strategies, achieving competitive performance with fewer parameters.

Contribution

It proposes a novel hybrid self-attention method to improve NEAT's performance on high-dimensional data, addressing input selection and network weight evolution.

Findings

Achieves comparable Atari game scores with fewer parameters.

Effectively selects important input features using self-attention.

Outperforms traditional evolutionary algorithms in high-dimensional tasks.

Abstract

This article presents a "Hybrid Self-Attention NEAT" method to improve the original NeuroEvolution of Augmenting Topologies (NEAT) algorithm in high-dimensional inputs. Although the NEAT algorithm has shown a significant result in different challenging tasks, as input representations are high dimensional, it cannot create a well-tuned network. Our study addresses this limitation by using self-attention as an indirect encoding method to select the most important parts of the input. In addition, we improve its overall performance with the help of a hybrid method to evolve the final network weights. The main conclusion is that Hybrid Self- Attention NEAT can eliminate the restriction of the original NEAT. The results indicate that in comparison with evolutionary algorithms, our model can get comparable scores in Atari games with raw pixels input with a much lower number of parameters.