Evolving Autonomous Agent Controllers as Analytical Mathematical Models
Paul Grouchy, Gabrielle D'Eleuterio · 2014
A novel Artificial Life paradigm is proposed where autonomous agents are controlled via genetically-encoded Evolvable Mathematical Models (EMMs). Agent/environment inputs are mapped to agent outputs via equation trees which are evolved using Genetic Pro-gramming. Equations use only the four basic mathematical operators: addition, subtraction, multiplication and division. Experiments on the discrete Double-T Maze with Homing problem are performed; the source code has been made available. Results demonstrate that autonomous controllers with learning capabilities can be evolved as analytical math-ematical models of behavior, and that neuroplasticity and neuromodulation can emerge within this paradigm without having these special functionalities specified a priori.