Establishing Trust in AI-based Tools for Game Development

AI-based tools to support the game development process have long been a topic in Game AI research, with popular publications in testing, churn prediction, asset, level and even game generation. However, the adaptation of these techniques from the games industry has been hesitant at best: The small-scale and simplified examples researchers use to demonstrate their work understandably only seldom convince the industry to risk investing in AI tools.

In this talk, I will speak about my experience establishing trust in AI-based tools to support creative processes in game development. Having worked on this topic in both industry and academia, I will address issues ranging from establishing a common language and explaining AI behaviour to issuing performance guarantees via benchmarking and theoretical analysis.

Vanessa Volz

Vanessa Volz is an AI researcher at modl.ai (Copenhagen, Denmark) where she works on AI-based game development tools for both automatic testing and supporting creativity. She received her PhD in 2019 from TU Dortmund University, Germany, for her work on surrogate-assisted evolutionary algorithms applied to optimisation problems in games. Her main research interest lies in analysing the behaviour and performance of optimisation algorithms, especially in the context of applications where human and artificial agents interact. Since interdisciplinary approaches offer large potential for improving understanding in these domains, she has co-founded and supports several initiatives to improve networking across different research fields and applications, as well as the games industry and academia. Her current research focus is on characterising problem landscapes of popular artifact generation methods in games.