Evolving Hebbian Learning Rules in Voxel-based Soft Robots

Abstract

<div>According to Hebbian theory, synaptic plasticity is the ability of neurons to strengthen or weaken the synapses among them in response to stimuli. It plays a fundamental role in the processes of learning and memory of biological neural networks. With plasticity, biological agents can adapt on multiple timescales and outclass artificial agents, the majority of which still rely on static Artificial Neural Network (ANN) controllers. In this work, we focus on Voxel-based Soft Robots (VSRs), a class of simulated artificial agents, composed as aggregations of elastic cubic blocks. We propose a Hebbian ANN controller where every synapse is associated with a Hebbian rule that controls the way the weight is adapted during the VSR lifetime. For a given task and morphology, we optimize the controller for the task of locomotion by evolving, rather than the weights, the parameters of the Hebbian rules. Our results show that the Hebbian controller is comparable, often better than a non-Hebbian baseline and that it is more adaptable to unforeseen damages. We also provide novel insights into the inner workings of plasticity and demonstrate that "true" learning does take place, as the evolved controllers improve over the lifetime and generalize well.</div>

On the Entanglement between Evolvability and Fitness: an Experimental Study on Voxel-based Soft Robots

“…In future works, we will extend the analysis of evolvability to the case of sensor evolution and learning, which have been recently addressed in the context of VSRs in (Ferigo et al, 2021a(Ferigo et al, , 2022 and (Ferigo et al, 2021b) respectively. Moreover, we will investigate how the proposed measure of evolvability correlate with some specific features of the fitness landscape, e.g., modality, as well as the behavior descriptors, which in turn may depend on the specific task (in the case of robots).…”