Unsupervised learning in metagame

    Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review


    The Metagame approach to computer game playing, introduced by Pell, involves writing programs that can play many games from some large class, rather than programs specialised to play just a single game such as chess. Metagame programs take the rules of a randomly generated game as input, then do some analysis of that game, and then play the game against an opponent. Success in Metagame competitions is evidence of a more general kind of ability than that possessed by (for example) a chess program or a draughts program. In this paper, we take up one of Pell’s challenges by building a Metagame player that can learn. The learning techniques used axe a refinement of the regression methods of Christensen and Korf, and they are applied to unsupervised learning, from self-play, of the weights of the components (or advisors) of the evaluation function. The method used leads to significant improvement in playing strength for many (but not all) games in the class. We also shed light on some curious behaviour of some advisor weights. In order to conduct this research, a new and more efficient Metagame player was written.
    Original languageEnglish
    Title of host publicationAdvanced Topics in Artificial Intelligence
    Subtitle of host publication12th Australian Joint Conference on Artificial Intelligence, Ar99 Sydney, Australia, December 6-10, 1999 Proceedings
    EditorsNorman Foo
    Place of PublicationBerlin Germany
    Number of pages12
    ISBN (Print)3540668225
    Publication statusPublished - 1999
    EventAustralasian Joint Conference on Artificial Intelligence 1999 - Sydney, Australia
    Duration: 6 Dec 199910 Dec 1999
    Conference number: 12th
    https://link.springer.com/book/10.1007/3-540-46695-9 (Proceedings)

    Publication series

    NameLecture Notes in Artificial Intelligence
    ISSN (Print)0302-9743


    ConferenceAustralasian Joint Conference on Artificial Intelligence 1999
    Abbreviated titleAI 1999
    Internet address

    Cite this