Search Results

< Back Visualising Generative Spaces Using Convolutional Neural Network Embeddings Link Author(s) O Withington, L Tokarchuk Abstract More info TBA Link

< Back Towards Mode Balancing of Generative Models via Diversity Weights Link Author(s) S Berns, S Colton, C Guckelsberger Abstract More info TBA Link

< Back Expressive curve editing with the sigma lognormal model Link Author(s) D Berio, FF Leymarie, R Plamondon Abstract More info TBA Link

< Back Less is More: Analysing Communication in Teams of Strangers Link Author(s) E Tan, A Wade, A Kokkinakis, G Heyes, SP Demediuk, A Drachen Abstract More info TBA Link

< Back Action Selection in the Creative Systems Framework Link Author(s) S Linkola, C Guckelsberger, A Kantosalo Abstract More info TBA Link

< Back The Ethics of Creative AI Link Author(s) C Flick, K Worrall Abstract More info TBA Link

< Back Applying and Visualising Complex Models in Esport Broadcast Coverage Link Author(s) A Pedrassoli Chitayat, F Block, JA Walker, A Drachen Abstract More info TBA Link

< Back On (Emergent) Systematic Generalisation and Compositionality in Visual Referential Games with Straight-Through Gumbel-Softmax Estimator Link Author(s) K Denamganaï, JA Walker Abstract More info TBA Link

< Back Noise reduction and targeted exploration in imitation learning for abstract meaning representation parsing Link Author(s) J Goodman, A Vlachos, J Naradowsky Abstract More info TBA Link

Automatic Evaluation of Tabletop Games Theme Game AI Project proposed & supervised by Diego Pérez-Liébana To discuss whether this project could become your PhD proposal please email: diego.perez@qmul.ac.uk < Back Automatic Evaluation of Tabletop Games Project proposal abstract: Modern Tabletop games are complex environments that combine multiple components: cards, tokens, boards, mechanics and rules. The amount, type and parameter values for each of these components affect the playability and balance of the game, influencing how the game is perceived by players and what strategies are better to win. This project proposal aims to research and develop methods to accurately evaluate the impact of each of these components in different aspects of gameplay, such as dominant strategies and game balance. In particular, the focus is set in large and complex games where it is computationally unaffordable to evaluate old or new content by playing the full game. The outcome of this project can lead not only to advance the state of the art in automatic evaluation techniques for existing games, but also to evaluate the impact of new components or mechanics in a game in development. Supervisor: Diego Pérez-Liébana Based at:

< Back Deep Learning for the Synthesis of Sound Effects Link Author(s) A Barahona-Rios Abstract More info TBA Link

< Back Strategy Games: The Components of A Worthy Opponent Link Author(s) D Gomme, R Bartle Abstract More info TBA Link