World Models, Action Selection, Embodied Concept Formation, and Conditioning

There are many computational models whose broad purpose is to allow an agent to learn via experience to perform effectively in a given environment However, it is uncommon to see these models directly compared to each other, or to empirical data of real creatures adapting to their environments. Here, a comparison methodology is proposed involving various known results in classical and operant conditioning and concept formation. The project involves examining a broad selection of computational models in various environments, and also mixing and matching components from these different models.