EvoTanks: co-evolutionary development of game-playing agents

Thomas Thompson, John Levine, Gillian Hayes

Research output: Contribution to conferencePaper

5 Citations (Scopus)
73 Downloads (Pure)


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.
Original languageEnglish
Number of pages6
Publication statusPublished - 4 Jun 2007
EventIEEE 2007 Symposium on Computational Intelligence and Games (CIG '07) - Hawaii, USA
Duration: 1 Apr 20075 Apr 2007


ConferenceIEEE 2007 Symposium on Computational Intelligence and Games (CIG '07)
CityHawaii, USA


  • evotanks
  • artificial intelligence
  • video games
  • games technology


Dive into the research topics of 'EvoTanks: co-evolutionary development of game-playing agents'. Together they form a unique fingerprint.

Cite this