Hero recommendation is formulated as a sequential decision making problem and solved using Monte Carlo Tree Search (UCT).
Zhengxing Chen, Truong-Huy D. Nguyen, Yuyu Xu, Chris Amato, Seth Cooper, Yizhou Sun, Magy Seif El-Nasr
RecSys,
2018
8207 articles from 48 game research venues are analyzed using network mining and flow visualization, to find 7 dominant sub-communities and 2 major trends (Educational Games and Mixed Reality).
Truong-Huy D. Nguyen, Edward Melcer, Alessandro Canossa, Katherine Isbister, Magy Seif El-Nasr
Entertainment Computing,
2018
A spatio-temporal interactive visualization tool, G-Player, is introduced. The heatmap-based tool provides binary operations on generated heat maps to answer complex, sequential queries on players’ behaviors.
Alessandro Canossa, Truong-Huy D Nguyen, Magy Seif El-Nasr
DiGRA-FDG,
2016
We present our efforts in designing virtual characters that can exhibit non-verbal behaviors to reflect varying degrees of warmth and competence, two personality traits shown to underlie social judgments and form stereotypical perception. Our experiments show that these dimensions of personality are perceived faithfully by observers.
Truong-Huy D Nguyen, Elin Carstensdottir, Nhi Ngo, Magy Seif El-Nasr, Matt Gray, Derek Isaacowitz, David DeSteno
IVA,
2015
A coordinated multi-view visualization, namely Glyph, is introduced. Designed to allow easy comparison of sequential behavior data, it comprises of two coordinated views that show moment-to-moment data as well as overall accumulated sequence difference. The tool’s utility is demonstrated to understand player behaviors in Wuzzit Trouble, a commercial math game.
Truong-Huy Dinh Nguyen, Magy Seif El-Nasr, Alessandro Canossa
FDG,
2015
The Aux technique, introduced in the ECML/PKDD 2012 paper, is extended to other sampling-based algorithms such as Sparse Sampling and FSSS, with theoretical guarantee. Numerical evaluations demonstrate the utility of the proposed technique.
Truong-Huy Dinh Nguyen, Tomi Silander, Wee-Sun Lee, Tze-Yun Leong
ICAPS,
2014
A novel technique, namely Aux, to enhance UCT with even potentially bad heuristics is proposed. Numerical evaluations demonstrate the utility of the proposed technique.
Truong-Huy Dinh Nguyen, Wee-Sun Lee, Tze-Yun Leong
ECML/PKDD,
2012
A framework to construct autonomous assistant, namely CAPIR, is proposed. Experiments show that the method provides near-human performance in collaborating with a human player in a maze game.
Truong-Huy Dinh Nguyen, David Hsu, Wee-Sun Lee, Tze-Yun Leong, Leslie Pack Kaelbling, Tomas Lozano-Perez, Andrew Haydn Grant
AIIDE,
2011