Work

A Comparison of Genetic Algorithms using Super Mario Bros.

Year: 2015
Type: article
Abstract: This project was designed to compare and contrast Evolving Behavior Trees (EBTs) with NeuroEvolution of Augmenting Topologies (NEAT), a Genetic Algorithm for the evolution of Artificial Neural Networks. We used Super Mario Bros. as a benchmark to compare these two techniques. The results showed that NEAT had a slightly higher maximum fitness while performing poorly in all other comparisons. EBTs performed strongly in rise time, evolution time, generalization, and complexity.
Source: Digital WPI
Language: English
Open Access status: green
OpenAlex ID: W3139022930
FWCI:
Cites: 7
Cited by: 1
Related to: 10