Multi-agent strategic modeling in a robotic soccer domain

ABSTRACT

This paper presents an algorithm for multi-agent strategic modeling (MASM) applied in a robotic soccer domain. It transforms a multi-agent action sequence into a set of strategic action descriptions in a graphical and symbolic form. By using hierarchically ordered domain knowledge, the algorithm is able to generate graphic and symbolic strategic action descriptions together with corresponding rules at different levels of abstraction. The method was evaluated on the RoboCup Soccer Server Internet League data.

REFERENCES

• 1: A. Bezek: Modeling Multiagent Games Using Action Graphs. Proceedings of Modeling Other Agents from Observations (MOO 2004), 2004.
• 2: Andraz Bezek, Discovering strategic multi-agent behavior in a robotic soccer domain, Proceedings of the fourth international joint conference on Autonomous agents and multiagent systems, July 25-29, 2005, The Netherlands [doi>10.1145/1082473.1082681]
• 3: J. Calmet, A. Daemi: From Entropy to Ontology. Proceedings of Fourth International Symposium From Agent Theory to Agent Implementation, 2004.
• 4: William W. Cohen , Yoram Singer, A simple, fast, and effective rule learner, Proceedings of the sixteenth national conference on Artificial intelligence and the eleventh Innovative applications of artificial intelligence conference innovative applications of artificial intelligence, p.335-342, July 18-22, 1999, Orlando, Florida, United States
• 5: Shoji Hirano , Shusaku Tsumoto, Finding interesting pass patterns from soccer game records, Proceedings of the 8th European Conference on Principles and Practice of Knowledge Discovery in Databases, p.209-218, September 20-24, 2004, Pisa, Italy
• 6: G. Kaminka in D. Avrahami: Symbolic Behavior-Recognition. Proceedings of Modeling Other Agents from Observations (MOO 2004), 2004.
• 7: G. Kaminka, M. Fidanboylu, A. Chang, in M. Veloso: Learning the sequential coordinated behavior of teams from observations. Proceedings of the RoboCup-2002 Symposium, 2002.
• 8: D. Koller and B. Milch: Multi-Agent Influence Diagrams for Representing and Solving Games. Games and Economic Behavior, 45(1), pp. 181--221, 2003.
• 9: G. Kuhlmann, P. Stone, and J. Lallinger: The UT Austin Villa 2003 Champion Simulator Coach: A Machine Learning Approach. In Daniele Nardi, et al., editors, RoboCup-2004: Robot Soccer World Cup VIII, Springer Verlag, Berlin, 2005.
• 10: Ranjit Nair , Milind Tambe , Stacy Marsella, Role allocation and reallocation in multiagent teams: towards a practical analysis, Proceedings of the second international joint conference on Autonomous agents and multiagent systems, July 14-18, 2003, Melbourne, Australia [doi>10.1145/860575.860664]
• 11: Stephen Sean Intille , Aaron F. Bobick, Visual recognition of multiagent action, 1999
• 12: Itsuki Noda , Sho'ji Suzuki , Hitoshi Matsubara , Minoru Asada , Hiroaki Kitano, Overview of RoboCup-97, RoboCup-97: Robot Soccer World Cup I, p.20-41, January 1998
• 13: T. Raines, M. Tambe, and S. Marsella: Towards automated team analysis: a machine learning approach. Third international RoboCup competitions and workshop, 1999.
• 14: RoboCup 2004: RoboCup Simulation League. RoboCup04 world cup game repository, http://carol.science.uva.nl/~jellekok/robocup/rc04/, 2004.
• 15: T. Steffens et. al: RoboCup Special Interest Group on Multi-Agent Modelling. http://www.cogsci.uni-osnabrueck.de/~tsteffen/mamsig/, 2001.
• 16: Gita Sukthankar , Katia Sycara, A cost minimization approach to human behavior recognition, Proceedings of the fourth international joint conference on Autonomous agents and multiagent systems, July 25-29, 2005, The Netherlands [doi>10.1145/1082473.1082635]
• 17: Dicky Suryadi , Piotr J. Gmytrasiewicz, Learning models of other agents using influence diagrams, Proceedings of the seventh international conference on User modeling, p.223-232, June 1999, Banff, Canada

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.6 Learning
          Subjects: Concept learning

General Terms:
Algorithms, Experimentation

Keywords:
RoboCup, multi-agent strategic modeling, strategy