KI - Künstliche Intelligenz

, Volume 25, Issue 1, pp 63–66 | Cite as


  • Michael ThielscherEmail author


The Game Description Language (GDL) used in the past AAAI competitions allows to tell a system the rules of arbitrary finite games that are characterised by perfect information, but does not extend to games in which players have asymmetric information, e.g. about their own hand of cards, or which involve elements of chance like the roll of dice. Accordingly, contemporary general game-playing systems are not designed to play games such as Backgammon, Poker or Diplomacy. GDL-II (for: GDL with Incomplete/Imperfect Information) is a recent extension of the original description language that makes general game playing truly general, because it allows to describe just any finite game with arbitrary forms of randomness as well as imperfect/incomplete information. This brings along the challenge to build the next generation of truly general game-playing systems that are able to understand any game description given in GDL-II and to learn to master these types of games, too.


General game playing Knowledge representation Imperfect information games 


  1. 1.
    Grosz B, Kraus S, Talman S, Stossel B, Havlin M (2004) The influence of social dependencies on decision-making: initial investigations with a new game. In: Proceedings of the international conference on autonomous agents and multiagent systems (AAMAS), New York, pp 782–789 Google Scholar
  2. 2.
    Png I (1983) Strategic behaviour in suit, settlement, and trial. Bell J Econ 14(2):539–550 CrossRefGoogle Scholar
  3. 3.
    Pritchard D (1994) The encycolpedia of chess variants. Godalming Google Scholar

Copyright information

© Springer-Verlag 2010

Authors and Affiliations

  1. 1.School of Computer Science and EngineeringThe University of New South WalesSydneyAustralia

Personalised recommendations