DeepAI AI Chat
Log In Sign Up

Evolving and Merging Hebbian Learning Rules: Increasing Generalization by Decreasing the Number of Rules

by   Joachim Winther Pedersen, et al.

Generalization to out-of-distribution (OOD) circumstances after training remains a challenge for artificial agents. To improve the robustness displayed by plastic Hebbian neural networks, we evolve a set of Hebbian learning rules, where multiple connections are assigned to a single rule. Inspired by the biological phenomenon of the genomic bottleneck, we show that by allowing multiple connections in the network to share the same local learning rule, it is possible to drastically reduce the number of trainable parameters, while obtaining a more robust agent. During evolution, by iteratively using simple K-Means clustering to combine rules, our Evolve and Merge approach is able to reduce the number of trainable parameters from 61,440 to 1,920, while at the same time improving robustness, all without increasing the number of generations used. While optimization of the agents is done on a standard quadruped robot morphology, we evaluate the agents' performances on slight morphology modifications in a total of 30 unseen morphologies. Our results add to the discussion on generalization, overfitting and OOD adaptation. To create agents that can adapt to a wider array of unexpected situations, Hebbian learning combined with a regularising "genomic bottleneck" could be a promising research direction.


page 1

page 2

page 3

page 4


Evolving Agents for the Hanabi 2018 CIG Competition

Hanabi is a cooperative card game with hidden information that has won i...

Testing the Genomic Bottleneck Hypothesis in Hebbian Meta-Learning

Recent work has shown promising results using Hebbian meta-learning to s...

AnyMorph: Learning Transferable Polices By Inferring Agent Morphology

The prototypical approach to reinforcement learning involves training po...

Evolution of control with learning classifier systems

In this paper we describe the application of a learning classifier syste...

Learning Generalizable Behavior via Visual Rewrite Rules

Though deep reinforcement learning agents have achieved unprecedented su...

ReNN: Rule-embedded Neural Networks

The artificial neural network shows powerful ability of inference, but i...

What Robot do I Need? Fast Co-Adaptation of Morphology and Control using Graph Neural Networks

The co-adaptation of robot morphology and behaviour becomes increasingly...