Fertility During Learning In Evolutionary Robot Systems

I’m excited to share that the paper “Fertility During Learning In Evolutionary Robot Systems” lead by Jacopo Michele Di Matteo and co-authored by Prof. Dr. Guszti Eiben and myself has been accepted at GECCO 2025, one of the top ranking conferences in evolutionary computing. This work investigates the performance differences when adapting fertility conditions for evolvable robots.

Abstract:

Robot evolution systems in which bodies and brains evolve in tandem can be significantly improved by extending them with the ability to learn. Technically, this means that ‘newborn’ robots are given the opportunity to optimize their inherited brain to control the inherited body adequately. Robots are in an underdeveloped ‘infant’ stage during this learning stage since their brains and fitness are still being improved. An open issue with regard to this infancy period is that of ‘fertility’: Should the robot be eligible for mating during the learning stage? This paper explores two distinct approaches from the literature, based on the Triangle of Life (TOL) model, where infant robots cannot produce offspring, and the Morphological Innovation Protection (MIP) mechanism, where they can. The main contribution is a new algorithm, TOL with infant fertility, inspired by MIP. Experimental comparisons with TOL and MIP show that the new method is superior; infant fertility makes TOL successful not only in producing robots with much higher fitness but also in maintaining the diversity of populations at high levels and in evolving interesting morphologies.