Investigation of Evolving Populations of Adaptive Agents

Abstract

AbstractWe investigate an evolution model of adaptive self-learning agents. The control system of agents is based on a neural network adaptive critic design. Each agent is a broker that predicts stock price changes and uses its predictions for action selection. We analyzed different regimes of learning and evolution and demonstrated that 1) evolution and learning together are more effective in searching for the optimal agent policy than evolution alone or learning alone; 2) in some regimes the Baldwin effect (genetic assimilation of initially acquired adaptive learning features during the course of Darwinian evolution) is observed; 3) inertial switching between two behavioral tactics similar to searching adaptive behavior of simple animals takes place during initial stages of evolutionary processes.KeywordsStock PriceAgent ResourceAdaptive AgentBaldwin EffectGenetic AssimilationThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.