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.
Highlights
NeuroEvolution of Augmenting Topologies (NEAT) is one of the most influential algorithms for evolving the topology and weights of neural networks
Novelty search produces higher success rates and average best fitness than fitness-based search, confirming the findings reported in [15]
Crossover seems to be helpful for fitness-based NEAT, in this specific case
Summary
NeuroEvolution of Augmenting Topologies (NEAT) is one of the most influential algorithms for evolving the topology and weights of neural networks. In [28], the behaviour of the classic NEAT algorithm with and without recombination was analysed on two simple benchmark functions: XOR and double-pole balancing. Several studies report contrasting views on the role of recombination in NEAT, as discussed in detail in “Related Work”. A recent systematic review of NEAT [25] urges for revisiting the roles of its various components and operators. Such studies are relevant as NEAT-specific operators render it incompatible with many other evolutionary algorithms, and NEAT cannot always benefit from advancements in the field [14]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
