Maurice H. J. Bergsma

Learn More
Solving a game is an exciting task; there, game solvers are looking for new achievements in research. In the last 25 years quite some games have been solved [van den Herik et al. (2002)]. Here solving means that the program is always able to achieve the best (i.e., game-theoretic) value independent of the opponent. This is called weakly solving a game(More)
The quality of AI opponents often leaves a lot to be desired, which poses many attractive challenges for AI researchers. In this respect, Turn-based Strategy (TBS) games are of particular interest. These games are focussed on high-level decision making, rather than low-level behavioural actions. For efficiently designing a TBS AI, in this paper we propose a(More)
Opponent modeling is a technique in computer game-playing which attempts to create a model of an opponent’s strategy. This model can then be used to predict the opponent’s future actions. This paper attempts to apply opponent modeling to the commercial card game Machiavelli, a game containing imperfect information. Neural networks are used to build the(More)
  • 1