Multi-game playing — A challenge for computational intelligence

In this paper, we deal with the topic of multi-game playing, i.e. creating agents able to autonomously learn to play any game within some arbitrarily defined genre. We describe the motivation for research in this particular area and briefly summarize the most important undertakings. Subsequently, we present a relatively young multi-game playing platform, called the General Game Playing (GGP) and our approach to development of GGP agent followed by some experimental results.