CI in General Game Playing - To Date Achievements and Perspectives

Multigame playing agents are programs capable of autonomously learning to play new, previously unknown games. In this paper, we concentrate on the General Game Playing Competition which defines a universal game description language and acts as a framework for comparison of various approaches to the problem. Although so far the most successful GGP agents have relied on classic Artificial Intelligence approaches, we argue that it would be also worthwhile to direct more effort to construction of General Game Players based on Computational Intelligence methods. We point out the most promising, in our opinion, directions of research and propose minor changes to GGP in order to make it a common framework suited for testing various aspects of multi-