Modelling Behaviour Change using Cognitive Agent Simulations

In health psychology, Behaviour Change Theories (BCTs) play an important role in modelling human goal achievement in adverse environments. Some of these theories use concepts that are also used in computational modelling of cognition and affect in AI. Examples include dual-process architecture and models of motivation. It is therefore important to ask whether some BCTs can be computationally implemented as cognitive agents in a way that builds on existing AI research in cognitive architecture. This paper presents work-in-progress research to apply selected behaviour change theories to simulated agents, so that an agent is acting according to the theory while attempting to complete a task in a challenging scenario. Two behaviour change theories are selected as examples (CEOS and PRIME). The research is focusing on complex agent architectures required for self-determined goal achievement in adverse circumstances where the action is difficult to maintain (e.g. healthy eating at office parties). Such simulations are useful because they can provide new insights into human behaviour change and improve conceptual precision. In addition, they can act as a rapid-prototyping environment for technology development. High-level descriptive simulations also provide an opportunity for transparency and participatory design, which is important for user ownership of the behaviour change process.