Creative Behaviour in Evolving Agents
Abstract
Computational creativity is a field of research that is primarily focused on music composition, art and linguistics. However, research pertaining to computational creativebehaviour is sparse. There is no clear, established methodology when it comes to makingagents behave creatively, or how to apply machine learning techniques to make themdo so.Using Evolutionary Algorithms (EAs), agents were evolved using different modular parts.The parts were several sensors and actuators that the agents used to solve tasks givento them. Their behaviour was determined by three different Artificial Intelligence (AI)methods. This thesis looks into how these three AI methods, namely Continuous TimeRecurrent Neural Network (CTRNN), Fuzzy Logic, and NeuroEvolution of AugmentingTopologies (NEAT), performed when evolving behaviour in the evolving agents. In orderto investigate this, a system capable of evolving and visualising agents in differentenvironments was developed.The results of using these methods show few signs of the evolution of creative behaviour.Instead, the agents simply evolved to solve a given task. However, some unexpectedactions can arguably be considered creative.This thesis contains the following contributions: A study of how different AI methodsperform when evolving creatures to behave creatively, and an implemented systemthat evolves creatures in different environments using the three AI methods mentionedabove.