Artificial life agents need complex environments for social learning
Environmental requirements for the use of social information by artificial life agents using evolved plastic artificial neural networks
Artificial Intelligence
Summary
The authors studied how artificial life agents might learn from each other in different environments. They found that simple tasks could be solved quickly without needing to learn from others. This suggests that social learning in artificial agents only evolves when the environment is complex enough to make social information useful. Their work helps explain when and why social learning might develop in artificial systems.
What this means in practice
- •For robotics developers: Design robot learning systems that include social information only when operating in complex environments where individual sensing is insufficient.
- •For multi-agent system engineers: Build agent collaboration strategies that activate social learning mechanisms in environments with high complexity for improved task performance.
Authors
Hugh Charterton, James M. Borg, Aniko Ekart
Abstract
Evolved Plastic Artificial Neural Networks (EPANNs) consist of two principal processes, the first, evolution, and the second, development and in-life learning. In the context of the origins of social = learning, very few studies have been carried out using ALIFE models based on EPANN requirements. Studies in this field have usually involved an imitative teacher/pupil relationship. This, however, ignores the possibility that the observed behaviour is a consequence of social information cues rather than direct imitation or teaching. Starting with the first of the EPANN processes (evolution), a series of experiments was undertaken using artificial neural network (ANN) based agents in a variety of foraging environments to examine under what minimal environmental conditions the use of social information might have evolved, as measured by the number of generations taken to meet a specified fitness criterion. NEAT (Neuroevolution of Augmenting Topologies) was the ANN used as its evolutionary algorithm would evolve a network's topology as well its weights. Unintentionally, in the experiment there was a simple network topology based on the location of the nearest food item which enabled agents to swiftly meet the fitness criterion. With this topology, additional information, social or otherwise, was not required and could have proved to be a hindrance. However, this does indicate that for the use of social information to have evolved, it would require a greater degree of complexity in the environment to do so.