Learning in distributed artificial intelligence systems

Over the last four decades, machine learning's primary interest has been single agent learning. In general, single agent learning involves improving the performance or increasing the knowledge of a single agent [5]. An improvement in performance or an increase in knowledge allows the agent to solve past problems with better quality or efficiency. An increase in knowledge may also allow the agent to solve new problems. An increase in performance is not necessarily due to an increase in knowledge. It may be brought about simply by rearranging the existing knowledge or utilizing it in a different manner. In addition, new knowledge may not be employed immediately but may be accumulated for future use. Single agent learning systems may be classified according to their underlying learning strategies. These strategies are ordered according to the amount of inferencing or the degree of knowledge transformation required by the learning system. This order also reflects the increasing amount of effort required by the learning system and the decreasing effort required by the teacher. These strategies are separated into the following six categories [10]: