NeuroEvolution of Augmenting Topologies (NEAT) is a system for evolving neural network topologies along with weights that has proven highly effective and adaptable for solving challenging reinforcement learning tasks. This paper analyses NEAT through the lens of Search Trajectory Networks (STNs), a recently proposed visual approach to study the dynamics of evolutionary algorithms. Our goal is to improve the understanding of neuroevolution systems. We present a visual and statistical analysis contrasting the behaviour of NEAT, with and without using the crossover operator, when solving the two benchmark problems outlined in the original NEAT article: XOR and double-pole balancing. Contrary to what is reported in the original NEAT article, our experiments without crossover perform significantly better in both domains.

A network-based modelling technique, search trajectory networks (STNs), has recently helped to understand the dynamics of neuroevolution algorithms such as NEAT. Modelling and visualising variants of NEAT made it possible to analyse the dynamics of search operators. Thus far, this analysis was applied directly to the NEAT genotype space composed of neural network topologies and weights. Here, we extend this work, by illuminating instead the behavioural space, which is available when the evolved neural networks control the behaviour of agents. Recent interest in behaviour characterisation highlights the need for divergent search strategies. Quality-diversity and Novelty search are examples of divergent search, but their dynamics are not yet well understood. In this article, we examine the idiosyncrasies of three neuroevolution variants: novelty, random and objective search operating as usual on the genotypic search space, but analysed in the behavioural space. Results show that novelty is a successful divergent search strategy. However, its abilities to produce diverse solutions are not always consistent. Our visual analysis highlights interesting relationships between topological complexity and behavioural diversity which may pave the way for new characterisations and search strategies.

No abstract

Neuroevolution has re-emerged as an active topic in the last few years. However, there is a lack of accessible tools to analyse, contrast and visualise the behaviour of neuroevolution systems. A variety of search strategies have been proposed such as Novelty search and Quality-Diversity search, but their impact on the evolutionary dynamics is not well understood. We propose using a data-driven, graph-based model, search trajectory networks (STNs) to analyse, visualise and directly contrast the behaviour of different neuroevolution search methods. Our analysis uses NEAT for solving maze problems with two search strategies: novelty-based and fitness-based, and including and excluding the crossover operator. We model and visualise the trajectories, contrasting and illuminating the behaviour of the studied neuroevolution variants. Our results confirm the advantages of novelty search in this setting, but challenge the usefulness of recombination.

No abstract