+++ Update 10/2020: FutureWorkGBG: Project themes in GBG for students (PDF) +++
(see also: GBG: General Board Games in CIOP )
Games are interesting in computer science concerning the question whether a computer can learn the game strategies just from self-play, without explicitly programming the tactics or performing exhaustive search. This is a branch of artificial intelligence (AI). Many game learning approaches are based on reinforcement learning, namely TD-learning.
In our research group we have studied extensively the game Connect-4 ("Four-in-a-Row"). We were able to develop an agent which learns Connect-4 nearly perfectly just from self-play. Our Java-based Connect-4 Game Playing Framework (C4GPF) is open-source for interested researchers. Read more...
The long-term goal of our research group is it to transfer these learning strategies to many other games (dots-and-boxes, go, Poker, checkers, Abalone, Sim, Othello, ...). The project is related to the research field known as General Game Playing (GGP). The aim of GGP is it to develop agents which are able to learn a great variety of games.