Skip to main content
SpringerLink
Log in

A GGP Feature Learning Algorithm

  • Fachbeitrag
  • Published:
KI - Künstliche Intelligenz Aims and scope Submit manuscript

Abstract

This paper presents a learning algorithm for two-player, alternating move GGP games. The Game Independent Feature Learning algorithm, GIFL, uses the differences in temporally-related states to learn patterns that are correlated with winning or losing a GGP game. These patterns are then used to inform the search. GIFL is simple, robust and improves the quality of play in the majority of games tested. GIFL has been successfully used in the GGP program Maligne.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

References

  1. Genesereth M, Love N, Pell B (2005) General game playing: overview of the AAAI competition. AI Mag 26(2):62–72

    Google Scholar 

  2. Group SL. http://logic.stanford.edu

  3. Kirci M (2009) Feature learning using state differences. Master’s thesis, Computing Science, University of Alberta

  4. Kirci M, Sturtevant N, Schaeffer J (2009) Feature learning using state differences. In: IJCAI workshop on general game playing

    Google Scholar 

  5. Kocsis L, Szepesvári C (2006) Bandit based Monte-Carlo planning. In: European conference on machine learning, pp 282–293

    Google Scholar 

  6. Kuhlmann G, Stone P (2007) Graph-based domain mapping for transfer learning in general games. In: Proceedings of the 18th European conference on machine learning, pp 188–200. http://z.cs.utexas.edu/users/ai-lab/pub-view.php?PubID=126628

    Google Scholar 

  7. Schaeffer J (1989) The history heuristic and alpha-beta search enhancements in practice. IEEE Trans Pattern Anal Mach Intell 11:1203–1212

    Article  Google Scholar 

  8. Sharma S, Kobti Z, Goodwin S (2008) Knowledge generation for improving simulations in UCT for general game playing. In: AI 2008: advances in artificial intelligence. Springer, Berlin, pp 49–55

    Chapter  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computing Science, University of Alberta, Edmonton, Alberta, Canada, T6G 2E8

    Mesut Kirci, Nathan Sturtevant & Jonathan Schaeffer

Authors
  1. Mesut Kirci
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Nathan Sturtevant
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jonathan Schaeffer
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Nathan Sturtevant.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Kirci, M., Sturtevant, N. & Schaeffer, J. A GGP Feature Learning Algorithm. Künstl Intell 25, 35–42 (2011). https://doi.org/10.1007/s13218-010-0081-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13218-010-0081-8

Keywords

Search

Navigation