Strathprints Home | Open Access | Browse | Search | User area | Copyright | Help | Library Home | SUPrimo

EvoTanks: co-evolutionary development of game-playing agents

Thompson, Thomas and Levine, John and Hayes, Gillian (2007) EvoTanks: co-evolutionary development of game-playing agents. In: IEEE 2007 Symposium on Computational Intelligence and Games (CIG '07), 2007-04-01 - 2007-04-05, Hawaii, USA.

[img]
Preview
PDF (strathprints003180.pdf)
Download (204Kb) | Preview

    Abstract

    This paper describes the EvoTanks research project, a continuing attempt to develop strong AI players for a primitive 'Combat' style video game using evolutionary computational methods with artificial neural networks. A small but challenging feat due to the necessity for agent's actions to rely heavily on opponent behaviour. Previous investigation has shown the agents are capable of developing high performance behaviours by evolving against scripted opponents; however these are local to the trained opponent. The focus of this paper shows results from the use of co-evolution on the same population. Results show agents no longer succumb to trappings of local maxima within the search space and are capable of converging on high fitness behaviours local to their population without the use of scripted opponents.

    Item type: Conference or Workshop Item (Paper)
    ID code: 3180
    Keywords: evotanks, artificial intelligence, video games, games technology, Electronic computers. Computer science
    Subjects: Science > Mathematics > Electronic computers. Computer science
    Department: Faculty of Science > Computer and Information Sciences
    Related URLs:
      Depositing user: Strathprints Administrator
      Date Deposited: 16 May 2007
      Last modified: 20 Jul 2013 21:49
      URI: http://strathprints.strath.ac.uk/id/eprint/3180

      Actions (login required)

      View Item

      Fulltext Downloads: