Evolving Self-taught Neural Networks: The Baldwin Effect and the Emergence of Intelligence
This work addresses the challenge of developing more adaptive and intelligent autonomous agents in multi-agent systems, though it appears incremental as it builds on existing concepts like the Baldwin Effect.
The paper tackles the problem of combining evolution and self-teaching in neural networks to enhance agent performance in foraging tasks, showing that their interplay outperforms either method alone and leads to intelligent foraging strategies.
The so-called Baldwin Effect generally says how learning, as a form of ontogenetic adaptation, can influence the process of phylogenetic adaptation, or evolution. This idea has also been taken into computation in which evolution and learning are used as computational metaphors, including evolving neural networks. This paper presents a technique called evolving self-taught neural networks - neural networks that can teach themselves without external supervision or reward. The self-taught neural network is intrinsically motivated. Moreover, the self-taught neural network is the product of the interplay between evolution and learning. We simulate a multi-agent system in which neural networks are used to control autonomous agents. These agents have to forage for resources and compete for their own survival. Experimental results show that the interaction between evolution and the ability to teach oneself in self-taught neural networks outperform evolution and self-teaching alone. More specifically, the emergence of an intelligent foraging strategy is also demonstrated through that interaction. Indications for future work on evolving neural networks are also presented.