A novel learning model for intelligent agents

The objective of this study is to synthesize a learning model capable of successful and effective operation in hard-to-model environments. Here, we are presenting a structurally simple and functionally flexible model. The model follows the learning patterns experienced by humans. The novelty of the adaptive model lies on the knowledge base and the learning strategy. The knowledge base is allowed to grow for as long as the agent lives. Learning is brought about by the interaction between two qualitatively different activities, leaving long-term and short-term marks on the behavior of the agent. The agent reaches conclusions using approximate reasoning. The focus of the model, the agent, starts life with a blank knowledge base, and learns as it lives. Classifiers are used to represent individual experiences. We demonstrate functionality of the model through a case study