Towards using first-person shooter computer games as an artificial intelligence testbed

  • Authors:
  • Mark Dawes;Richard Hall

  • Affiliations:
  • Dept. Computer Science & Engineering, La Trobe University, Melbourne, Victoria, Australia;Dept. Computer Science & Engineering, La Trobe University, Melbourne, Victoria, Australia

  • Venue:
  • KES'05 Proceedings of the 9th international conference on Knowledge-Based Intelligent Information and Engineering Systems - Volume Part I
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

One trend in first-person shooter computer games is to increase programmatic access. This allows artificial intelligence researchers to embed their cognitive models into stable artificial characters, whose competitiveness and realism can be evaluated with respect to human players. However, plugging cognitive models in is non-trivial, since games are currently not designed with AI researchers in mind. In this paper we introduce an intermediate architecture that fits between these game and the AI, and assess its feasibility by implementing it within the game Unreal Tournament 2004. Making such an architecture publicly available may potentially lead to improved quality of game AI.