Bootstrapping of memetic from genetic evolution via inter-agent selection pressures
This work addresses the problem of understanding memetic evolution in artificial systems for researchers in evolutionary computation and AI, but it is incremental as it builds on existing concepts without demonstrating practical benefits.
The study investigated how memetic evolution emerges from interactions between neural network agents and its interaction with genetic evolution, finding that inter-agent selection pressures are essential for bootstrapping high-fidelity meme replication and novelty, but the emergent meme layer had minimal impact on agents' task-solving abilities.
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