Game team balancing by using particle swarm optimization

Shih Wei Fang, Sai-Keung Wong*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

11 Scopus citations


Game balancing affects the gaming experience of players in video-games. In this paper, we propose a novel system, team ability balancing system (TABS), which is developed for automatically evaluating the performance of two teams in a role-playing video game. TABS can be used for assisting game designers to improve team balance. In TABS, artificial neural network (ANN) controllers learn to play the game in an unsupervised manner and they are evolved by using particle swarm optimization. The ANN controllers control characters of the two teams to fight with each other. An evaluation method is proposed to evaluate the performance of the two teams. Based on the evaluation results, the game designers can adjust the abilities of the characters so as to achieve team balance. We demonstrate TABS for our in-house MagePowerCraft game in which each team consists of up to three characters.

Original languageEnglish
Pages (from-to)91-96
Number of pages6
JournalKnowledge-Based Systems
StatePublished - 1 Oct 2012


  • Artificial neural network
  • Game balance
  • Particle swarm optimization
  • Role-playing game
  • Team balancing system


Dive into the research topics of 'Game team balancing by using particle swarm optimization'. Together they form a unique fingerprint.

Cite this