Using coevolution to understand and validate game balance in continuous games

ABSTRACT

We attack the problem of game balancing by using a coevolutionary algorithm to explore the space of possible game strategies and counter strategies. We define balanced games as games which have no single dominating strategy. Balanced games are more fun and provide a more interesting strategy space for players to explore. However, proving that a game is balanced mathematically may not be possible and industry commonly uses extensive and expensive human testing to balance games. We show how a coevolutionary algorithm can be used to test game balance and use the publicly available continuous state, capture-the-flag CaST game as our testbed. Our results show that we can use coevolution to highlight game imbalances in CaST and provide intuition towards balancing this game. This aids in eliminating dominating strategies, thus making the game more interesting as players must constantly adapt to opponent strategies.

REFERENCES

• 1: Peter J. Angeline , Jordan B. Pollack, Competitive Environments Evolve Better Solutions for Complex Tasks, Proceedings of the 5th International Conference on Genetic Algorithms, p.264-270, June 01, 1993
• 2: J. Ashlock, D.; Schonfeld. Nonlinear projection for the display of high dimensional distance data. Evolutionary Computation, 2005. The 2005 IEEE Congress on, 3:2776--2783 Vol. 3, 2-5 Sept. 2005.
• 3: D. Charles and M. Black. Dynamic player modeling: A framework for player-centered digital games. In International Conference on Computer Games: Artificial Intelligence, Design and Education, November 2004.
• 4: D. Charles, M. McNeill, M. McAlister, M. Black, A. Moore, K. Stringer, J. KAijcklich, and A. Kerr. Player-centered game design: Player modeling and adaptive digital games. In DiGRA 2005 Conference: Changing Views - Worlds in Play, 2005.
• 5: R. Dawkins and J. R. Krebs. Arms races between and within species. In Proceedings of the Royal Society of London, number 205 in Series B, pages 489--511, 1979.
• 6: David B. Fogel, Blondie24: playing at the edge of AI, Morgan Kaufmann Publishers Inc., San Francisco, CA, 2001
• 7: http://www.gamerankings.com/, January 28 2008.
• 8: David E. Goldberg, Genetic Algorithms in Search, Optimization and Machine Learning, Addison-Wesley Longman Publishing Co., Inc., Boston, MA, 1989
• 9: W. D. Hillis. Artificial Life II, chapter Co-evolving parasites improves simulated evolution as an optimization technique, pages 313--384. Addison-Wesley, 1997.
• 10: John H. Holland, Adaptation in natural and artificial systems, MIT Press, Cambridge, MA, 1992
• 11: P. Klepek. Npd fallout: Best selling games of 2007. http://www.1up.com/do/newsstory?cid=3165505.
• 12: R. E. Leigh, T. Morelli, S. J. Louis, M. Nicolescu, and C. Miles. Finding attack strategies for predator swarms using genetic algorithms. In Proceedings of the 2005 Congress of Evolutionary Computation, September 2005.
• 13: C. Miles and S. J. Louis. Co-evolving influence map tree based strategy game players. In 2007 IEEE Symposium on Computational Intelligence in Games. IEEE Press, 2007.
• 14: J. B. Pollack, A. D. Blair, and M. Land. Co-evolution of a backgammon player. In C. G. Langton and K. Shimohara, editors, Artificial Life V: Proc. of the Fifth Int. Workshop on the Synthesis and Simulation of Living Systems, pages 92--98, Cambridge, MA, 1997. The MIT Press.
• 15: J. Portnow. The fine art of balance. http://gamecareerguide.com/features/478/the_fine_art_of_.php.
• 16: Christopher D. Rosin , Richard K. Belew, New methods for competitive coevolution, Evolutionary Computation, v.5 n.1, p.1-29, Spring 1997 [doi>10.1162/evco.1997.5.1.1]

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.1 Applications and Expert Systems
          Subjects: Games

General Terms:
Design

Keywords:
artificial intelligence, coevolution, game balance, games