Grounding Action-Selection in Event-Based Anticipation

Can we use the constructed predictive model as a basis for action-selection? We develop an event-based anticipation framework for performing latent learning and we provide two mathematical tools to identify relevant relationships between events. These tools allow us to build a predictive model which is then embedded in an action-selection architecture to generate adaptive behavior. We first analyze some of the properties of the model in simple learning tasks. Its efficiency is then evaluated in a more complex task where the agent has to adapt to a changing environment. Adaptive Systems Research Group University of Hertfordshire