Adaptive and Robust Multi-Agent Systems

We applied tools based on quantitative genetic theory in order to improve Evolutionary Algorithms for use with team learning tasks. We reviewed the quantitative genetics literature more widely, and developed a theoretical analysis applying genetic theory to the team learning problem. We then constructed and analyzed a neural network structure and new genetic operators which more effectively divide the feature space for the Evolutionary Algorithm. We performed experiments and discovered that the new operators and structure produced more parsimonious results. We plan to publish these results in an upcoming conference following more rigorous experiments.