ADAPTATION AND LEARNING IN AN AUTONOMOUS PHYSICAL AGENT ARCHITECTURE

Learning and adaptation is presented for a specific but generally applicable autonomous physical agent (APA) architecture. The paper is providing a general framework of skills learning within behaviour logic framework of agents that communicate, sense and act in the physical world. It is shown how programmed playfulness can be easily implemented that results in learning and ultimately better skills of agents. Reusability of results in learning algorithms is supported by ontology based classification of learning in operational modes. Ontology based classification provides object instances that enable modularization of software and easy interfacing of operational modes with learning algorithms.