Bootstrapping of memetic from genetic evolution via inter-agent selection pressures

TL;DR

This paper investigates how memetic evolution can bootstrap from genetic evolution in an artificial agent system, highlighting the importance of inter-agent selection pressures for memetic emergence without significantly impacting task performance.

Contribution

It demonstrates that inter-agent selection pressures are crucial for the self-sustaining emergence of memetic evolution in neural network agents.

Findings

Memetic evolution requires inter-agent selection pressures to bootstrap.

Memetic layer emergence does not significantly affect task learning.

Agents can develop high-fidelity meme replication without task influence.

Abstract

We create an artificial system of agents (attention-based neural networks) which selectively exchange messages with each-other in order to study the emergence of memetic evolution and how memetic evolutionary pressures interact with genetic evolution of the network weights. We observe that the ability of agents to exert selection pressures on each-other is essential for memetic evolution to bootstrap itself into a state which has both high-fidelity replication of memes, as well as continuing production of new memes over time. However, in this system there is very little interaction between this memetic 'ecology' and underlying tasks driving individual fitness - the emergent meme layer appears to be neither helpful nor harmful to agents' ability to learn to solve tasks. Sourcecode for these experiments is available at https://github.com/GoodAI/memes