Game AI & Search (GAIS)
Search is a key reasoning technique. Research in Game Artificial Intelligence (AI) & Search therefore helps to increase the quality of automated decision-making, whether this is used to make the final decision autonomously or to provide a human with a range of sensible options.
This is an old research theme of the Department of Data Science and Knowledge Engineering (DKE). DKE has become the Department of Advanced Computing Sciences.
Automated decision-making takes on a central role in many fields. For example, in logistics, manufacturers create intelligent planning systems to manage their resources. Intelligent search algorithms assist chemists by generating a plan to transform compounds into simpler starting materials, and the gaming industry relies on realistic AI as opponents for its players.
Games also provide a test domain for the decision-making process of AI agents: the monitoring of game outcomes provides a straightforward way to measure their performance.
Research focus and application
The focus of the theme lies in the domain of AI that is able to play and design games. Besides performing research in abstract games in order to improve the playing strength (which ultimately results in finding the optimal strategy), research within GAIS focuses on four trends in the field:
- Developing AI that can outplay (human) opponents in games
- Video games as a test domain for AI research
- The design of agents which can play a diverse number of games (General Game Playing)
- Automatic game design/reconstruction or content generation for games
Scope
- Search techniques: proof number search, Monte-Carlo tree search, single agent search and multiplayer search
- Opponent modelling
- Combinatorial & positional games
- Procedural content generation
- Game design
- General (video) game playing
- Video game AI
- Digital modelling of traditional games
- Reconstruction of ancient games.
Go to GAIS website
This work is complemented by the Digital Ludeme Project, funded by an ERC grant of €2 million. The project introduces the field of Digital Archaeoludology, which combines computational and historical analyses of traditional games.
Game AI & Search in practice
Researchers
Tom Pepels
- PhD candidate
Highlighted publications
- Baier, H., & Winands, M. H. M. (2018). MCTS-Minimax Hybrids with State Evaluations. Journal of Artificial Intelligence Research, 62, 193-231. https://doi.org/10.1613/jair.1.11208
- Browne, C. (2018). Modern Techniques for Ancient Games. In 2018 IEEE Conference on Computational Intelligence and Games, CIG 2018, Maastricht, The Netherlands, August 14-17, 2018 (pp. 1-8)
- Browne, C., & Piette, E. (2019). Digital Archaeoludology. In Computer Applications and Quantitative Methods in Archaeology : (CAA'19)
- Crist, W. (2021). Debunking the Diffusion of Senet. Board Game Studies Journal, 15:1, pp. 13– 27
- Gaina, R. D., Couëtoux, A., Soemers, D. J. N. J., Winands, M. H. M., Vodopivec, T., Kirchgessner, F., Liu, J., Lucas, S. M., & Diego Perez-Liebana, D. (2018). The 2016 Two-Player GVGAI Competition. IEEE Transactions on Games, 10(2), 209-220. https://doi.org/10.1109/TCIAIG.2017.2771241
- Piette, E., Soemers, D. J. N. J., Stephenson, M., Sironi, C. F., Winands, M. H. M., & Browne, C. (2020). Ludii - The Ludemic General Game System. In G. De Giacomo, A. Catala, B. Dilkina, M. Milano, S. Barro, A. Bugarín, & J. Lang (Eds.), ECAI 2020 : 24th European Conference on Artificial Intelligence (Vol. 325, pp. 411-418). IOS Press. Frontiers in Artificial Intelligence and Applications https://doi.org/10.3233/FAIA200120
- Rossi, L., Winands, M. H. M., & Butenweg, C. (2021). Monte Carlo Tree Search as an intelligent search tool in structural design problems. Engineering with Computers. https://doi.org/10.1007/s00366-021-01338-2
- Sironi, C. F., Liu, J., & Winands, M. H. M. (2020). Self-Adaptive Monte Carlo Tree Search in General Game Playing. IEEE Transactions on Games, 12(2), 132-144. https://doi.org/10.1109/TG.2018.2884768
- Soemers, D. J. N. J., Brys, T., Driessens, K., Winands, M. H. M., & Nowé, A. (2018). Adapting to Concept Drift in Credit Card Transaction Data Streams Using Contextual Bandits and Decision Trees. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, New Orleans, Louisiana, USA, February 2-7, 2018: The Thirtieth AAAI Conference on Innovative Applications of Artificial Intelligence (IAAI-18) (pp. 7831-7836). AAAI Press. https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16183
- Stephenson, M., Renz, J., & Ge, X. (2020). The computational complexity of Angry Birds. Artificial Intelligence, 280, [103232]. https://doi.org/10.1016/j.artint.2019.103232