Autonomous Artificial Intelligent Agents
Iaroslav Omelianenko · 2022
Cities were built to facilitate trade and protection. A smart city environment can be considered a product of the evolutionary process built around the coevolution of multiple autonomous artificial intelligent agents (AAIAs). The central concept of a genetic algorithm is a population of candidate solutions that evolve to solve optimisation problems using the rules similar to the ones of natural selection, as in biological evolution. This chapter considers the encoding schemes of the genotype that can be used to represent the phenotypes of the artificial neural networks (ANNs). The neuroevolution is a methodology for training ANNs using an evolutionary process. The chapter deals with a description of the direct genome encoding scheme. The NeuroEvolution of Augmented Topologies algorithm was designed to address the drawbacks associated with direct genome encoding schemes. The chapter discusses the evolution of the AAIAs to solve the maze navigation problem using the novelty search optimisation method.