David Buckley
I am a PhD student studying Computer Science at The University of Manchester.
My research lies within the field of player modelling, specifically trying to predict how good players are from logs of their games. The focus of the research is in first-person shooters, notably Red Eclipse.
Player modelling attempts to construct models of players through the use of existing machine learning techniques. These models can be used as feedback for developers, providing insight into the workings of the players and their interactions with their games. Alternatively, they can be used for dynamically adapting the game to each player, creating a more immersive environment.
Current Research
I am working towards a journal paper on the topic of predicting skill while someone is playing. I intend to work on some applications of this, but more will follow soon.
Published Work
- D. Buckley, K. Chen, J. Knowles. Predicting skill from gameplay input to a first-person shooter. PDF
Past Experiments
Automatic Player Modelling Using Hardware Input
Players were asked to play several game sessions and provide feedback in order to construct models of players. Games were played on Red Eclipse, an open-source first-person shooter, for which a tutorial was provided.