Problem Solving with Unstructured Information

Learning is an integral part of intelligent agent's problem-solving ability. Most research works on learning assume that information be provided in a complete and well-structured manner and/or when rules are clearly specified. They have difficulties in handling cases with incomplete and unstructured data. This document presents an information retrieval based approach to deal with this difficulty. Preliminary experimental results show that information retrieval can effectively help an agent to analyze and solve the problems encountered.