Research Article Open Access

STRATEGY PATTERNS PREDICTION MODEL

Aram Baruch Gonzalez Perez1 and Jorge Adolfo Ramirez Uresti1
  • 1 , Mexico

Abstract

Multi-agent systems are broadly known for being able to simulate real-life situations which require the interaction and cooperation of individuals. Opponent modeling can be used along with multi-agent systems to model complex situations such as competitions like soccer games. In this study, a model for predicting opponent moves based on their target is presented. The model is composed by an offline step (learning phase) and an online one (execution phase). The offline step gets and analyses previous experiences while the online step uses the data generated by offline analysis to predict opponent moves. This model is illustrated by an experiment with the RoboCup 2D Soccer Simulator. The proposed model was tested using 22 games to create the knowledge base and getting an accuracy rate over 80%.

Journal of Computer Science
Volume 10 No. 1, 2014, 73-84

DOI: https://doi.org/10.3844/jcssp.2014.73.84

Submitted On: 21 May 2013 Published On: 12 November 2013

How to Cite: Perez, A. B. G. & Uresti, J. A. R. (2014). STRATEGY PATTERNS PREDICTION MODEL. Journal of Computer Science, 10(1), 73-84. https://doi.org/10.3844/jcssp.2014.73.84

  • 2,727 Views
  • 3,017 Downloads
  • 0 Citations

Download

Keywords

  • Opponent Modeling
  • Machine Learning
  • Case Based Reasoning