Learning Agent Goal Structures by Evolution

H. Van Dyke Parunak

Abstract: When social models test theories and make predictions about real scenarios, they must be fit to observed behaviors. Realistic modeling frameworks offer multiple interacting mechanisms, each with parameters that can be fit. Previously, we demonstrated how to fit the preferences that SCAMP agents use to make tactical decisions. This paper extends that work by reporting experiments on fitting the hierarchical goal networks that guide more strategic decisions.