loading page

Evolving Hebbian Learning Rules in Voxel-based Soft Robots
  • +1
  • Andrea Ferigo ,
  • Giovanni Iacca ,
  • Eric Medvet ,
  • Federico Pigozzi
Andrea Ferigo
Author Profile
Giovanni Iacca
University of Trento

Corresponding Author:[email protected]

Author Profile
Eric Medvet
Author Profile
Federico Pigozzi
Author Profile


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.
Sep 2023Published in IEEE Transactions on Cognitive and Developmental Systems volume 15 issue 3 on pages 1536-1546. 10.1109/TCDS.2022.3226556