Simulation of evolution of autonomous adaptive agents

A model of evolving populations of self-learning agents is studied and the interaction between learning and evolution is analyzed. Each agent is equipped with a neural network adaptive critic design for behavioral adaptation. The model is investigated for the case of a simple agent-broker that predicts stock price changes and uses its predictions for selecting actions. Three cases are analyzed in which either evolution or learning, or both, are active in this model. It is shown that the Baldwin effect can be observed in this model, viz., originally acquired adaptive policy of agents becomes inherited over the course of the evolution. Also the behavioral tactics of our agents is compared to the searching behavior of simple animals.