In this article, we explore how artificial swarm intelligence evolve through evolutionary algorithms aimed at reducing the system’s sensory surprise. We demonstrate the use of the free energy principle, borrowed from statistical physics, to describe quantitatively the optimization method (reduction of sensory surprise) that can be applied to support continuous learning.
The article deals with the problem of finding a solution for the navigational task of navigating a maze by an autonomous agent controlled by an artificial neural network (ANN). A solution to this problem was proposed by training the controlling ANN using the method of neuroevolution of augmenting topologies (NEAT).
In this paper, we look at how Artificial Swarm Intelligence can evolve using evolutionary algorithms that try to minimize the sensory surprise of the system. We will show how to apply the free-energy principle, borrowed from statistical physics, to quantitatively describe the optimization method (sensory surprise minimization), which can be used to support lifelong learning.
In this work we describe experiment of applying Novelty Search method of fitness function optimization combined with Neuro-Evolution of Augmenting Topologies (NEAT) algorithm to produce Autonomous Artificial Intelligent Agents capable to solve spatial navigation task in complex maze environment.