Neural networks for state evaluation in general game playing

Daniel Michulke, Michael Thielscher

    Research output: Contribution to journalArticlepeer-review

    Abstract

    Unlike traditional game playing, General Game Playing is concerned with agents capable of playing classes of games. Given the rules of an unknown game, the agent is supposed to play well without human intervention. For this purpose, agent systems that use deterministic game tree search need to automatically construct a state value function to guide search. Successful systems of this type use evaluation functions derived solely from the game rules, thus neglecting further improvements by experience. In addition, these functions are fixed in their form and do not necessarily capture the game's real state value function. In this work we present an approach for obtaining evaluation functions on the basis of neural networks that overcomes the aforementioned problems. A network initialization extracted from the game rules ensures reasonable behavior without the need for prior training. Later training, however, can lead to significant improvements in evaluation quality, as our results indicate.
    Original languageEnglish
    Pages (from-to)95-110
    Number of pages16
    JournalLecture Notes in Computer Science
    Volume5782
    Issue numberPART 2
    DOIs
    Publication statusPublished - 2009

    Fingerprint

    Dive into the research topics of 'Neural networks for state evaluation in general game playing'. Together they form a unique fingerprint.

    Cite this