STRATEGY PATTERNS PREDICTION MODEL

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%.