TechRxiv
preprint.pdf (5.13 MB)
Download file

Evolving Hebbian Learning Rules in Voxel-based Soft Robots

Download (5.13 MB)
preprint
posted on 16.12.2021, 14:14 by Andrea Ferigo, Giovanni IaccaGiovanni Iacca, Eric Medvet, Federico Pigozzi
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.

Funding

Google Faculty Research Award

History

Email Address of Submitting Author

giovanni.iacca@unitn.it

ORCID of Submitting Author

0000-0001-9723-1830

Submitting Author's Institution

University of Trento

Submitting Author's Country

Italy