Computer Science PGR Seminar Jess McGowan and Duong Phuc Tai Nguyen

Jess McGowan will present Roll for Insight: Can TTRPG Mechanics be Utilised for Persona Creation?

Abstract: Personas are a useful tool in user experience (UX) design, allowing designers to understand what specific users need a system to do to be successful. However, there is no real consistency in how personas are designed, and what is required to have an effective one.

Tabletop Role-Playing Games (TTRPGs) offer structured instructions and materials to aid players in building characters for gameplay. An exploratory study was carried out to establish the transferability of the character creation processes from games including Dungeons & Dragons and Daggerheart, to a persona creation framework as part of a TTRPG-UX environment. This talk will present the findings from the study.

Bio: Jess McGowan is a second-year PhD student working in HCI, more specifically about how personas are designed and used as part of the user experience design process. Their current research is examining how character creation mechanics in tabletop role-playing games can be leveraged to form a persona creation framework.

Duong Phuc Tai Nguyen will present Optimising the Optimisers: Reinforcement Learning as an Intelligent Pilot for Evolutionary Search

Abstract: Nature has spent billions of years perfecting adaptation through evolution. In the digital world, scientists harness these biological principles to solve massive challenges, from logistics and scheduling to complex “black-box” optimisation problems. However, these digital evolutionary processes are often “blind”, following rigid rules regardless of the terrain's complexity. In this talk, I explore the integration of a “digital brain” into this process using Reinforcement Learning. By training an AI agent to act as an intelligent pilot, it observes the evolution in real-time and dynamically adjusts optimiser's strategy to avoid traps and discover better solutions. This synergy transforms a blunt tool into a precision instrument, allowing us to solve the world's most complex problems with unprecedented speed and reliability.

Bio: Tai is a joint PhD student in Computer Science at the University of St Andrews and Sorbonne Université (France). His research interests lie at the intersection of machine learning and evolutionary optimisation.