PAGODA: An Integrated Architecture for Autonomous Agents

Contents

PAGODA (Probabilistic Autonomous GOal- Directed Agent) is an autonomous intelligent agent that explores a novel environment, building a model of the world and using the model to plan its actions [desJardins, 1992b]. PAGODA incorporates solutions to the problems of selecting learning tasks, choosing a learning bias, classifying observations, and performing induetire learning of world models under uncertainty, ill all integrated system for planning and learning in complex domains. This paper raises some key issues in building autonomous embedded agents and shows how PAGODA addresses these issues. The probabilistic learning mechanism that PAGODA uses to build its world model is described in more detail.