Abstract Forward Models for Modern Games

Team

Diego Perez-Liebana | Principal investigator

Diego Perez-Liebana is a Senior Lecturer in Computer Games and Artificial Intelligence at Queen Mary University of London (UK). He holds a Ph.D in Computer Science from the University of Essex (2015). His research is centred in the application of Artificial Intelligence to games, Tree Search and Evolutionary Computation. He is especially interested in the application of Statistical Forward Planning methods (such as Monte Carlo Tree Search and Rolling Horizon Evolutionary Algorithms) to modern games, General Video Game Playing, and strategy games. He has a long experience in organizing competitions for the Game AI community in recent years, including the Physical Traveling Salesman Problem, the GVGAI and the MARLO challenge.

Alexander Dockhorn | Research Associate

I studied Computer Science at the Otto-von-Guericke University (OvGU) in Magdeburg (Germany) and University of Abertay in Dundee (Scotland). Back in Magdeburg I finished my Master in Computer Science and after which I joined the Computational Intelligence research group lead by Prof. Rudolf Kruse and Prof. Sanaz Mostaghim. After finishing my PhD thesis on the topics forward model learning and predictive state determinization I joined the Game AI Research Group as a Postdoctoral Research Assistant. My current research interests are intelligent data analysis and more generalised methods for forward model learning.

Jorge Hurtado | Game Developer

In Semptember 2019, I graduated from ESNE (Spain, Madrid) with a Bachelor of Science degree in “Design and Videogame development”. The last year of my four year long bachelor, I studied abroad in Cologne Game Lab of the TH Köln – University of Applied Sciences (Germany). My main interest is artificial intelligence applied to videogames. I like to spend my spare time training and competing in Olympic Weightlifting.

Ethan Xu | PhD Student

Fresher at Game AI Group. Previously working on: Reinforcement Learning algorithm and its application on Game AI and Robotics; Multi-Task Learning. Currently, I am working on stable, robust and applicable Game AI.

Dominik Jeurissen | MSc Student

I’m a master student at Maastricht University (Netherlands), and I’m in my last year of the master’s programme “Artificial Intelligence”. I’ve worked as an intern at Queen Mary University since July 2019, and I’m planning to cooperate with QMUL for my master thesis. I’m very interested in researching efficient learning methods for Deep Learning. My main interests are topics like one-shot learning, intrinsic motivation and Hebbian plasticity. For my master thesis, I will research on how to enable search-algorithms to adapt quickly to a complex environment while searching.