Adaptability of Improved NEAT in Variable Environments

TL;DR

This paper investigates the adaptability of improved NEAT algorithms in changing environments, highlighting the effectiveness of recurrent connections and the trade-offs of other enhancements.

Contribution

It evaluates various improved NEAT versions in variable environments, demonstrating the significant impact of recurrent connections on performance.

Findings

Recurrent connections significantly improve NEAT performance in variable environments.

Automatic feature selection negatively impacts NEAT effectiveness.

Increasing population size reduces computation but slightly lowers performance.

Abstract

A large challenge in Artificial Intelligence (AI) is training control agents that can properly adapt to variable environments. Environments in which the conditions change can cause issues for agents trying to operate in them. Building algorithms that can train agents to operate in these environments and properly deal with the changing conditions is therefore important. NeuroEvolution of Augmenting Topologies (NEAT) was a novel Genetic Algorithm (GA) when it was created, but has fallen aside with newer GAs outperforming it. This paper furthers the research on this subject by implementing various versions of improved NEAT in a variable environment to determine if NEAT can perform well in these environments. The improvements included, in every combination, are: recurrent connections, automatic feature selection, and increasing population size. The recurrent connections improvement performed extremely well. The automatic feature selection improvement was found to be detrimental to performance, and the increasing population size improvement lowered performance a small amount, but decreased computation requirements noticeably.