Using the Opponent Pass Modeling method to improve defending ability of a (Robo)Soccer simulation team

Modeling agents' behavior has always been a challenge in multiagent systems. In a competitive environment, predicting future be- haviors of opponents helps to make plans to confront their actions prop- erly. We have used the RoboCup soccer server environment (1) to design a coach, capable of analyzing simulated soccer games and making deci- sions to improve teammate players' behavior during the games. We will introduce our "Opponent Pass Modeling" method which makes a model of opponent team's passing behavior to guard opponent players and as a result, to improve the defending behavior of our team. We will also de- scribe a new approach to evaluate coach algorithms using soccer server log-files and LogCoach tool.