Advertisement

Genetic Programming and Evolvable Machines

, Volume 14, Issue 2, pp 245–277 | Cite as

Controllable procedural map generation via multiobjective evolution

  • Julian Togelius
  • Mike Preuss
  • Nicola Beume
  • Simon Wessing
  • Johan Hagelbäck
  • Georgios N. Yannakakis
  • Corrado Grappiolo
Article

Abstract

This paper shows how multiobjective evolutionary algorithms can be used to procedurally generate complete and playable maps for real-time strategy (RTS) games. We devise heuristic objective functions that measure properties of maps that impact important aspects of gameplay experience. To show the generality of our approach, we design two different evolvable map representations, one for an imaginary generic strategy game based on heightmaps, and one for the classic RTS game StarCraft. The effect of combining tuples or triples of the objective functions are investigated in systematic experiments, in particular which of the objectives are partially conflicting. A selection of generated maps are visually evaluated by a population of skilled StarCraft players, confirming that most of our objectives correspond to perceived gameplay qualities. Our method could be used to completely automate in-game controlled map generation, enabling player-adaptive games, or as a design support tool for human designers.

Keywords

Real-time strategy games RTS Procedural content generation Evolutionary computation Multiobjective optimisation StarCraft 

Notes

Acknowledgments

This research was supported in part by the Danish Research Agency project AGameComIn (number 274-09-0083) and in part by the EU FP7 ICT project SIREN (number 258453). As stated in the introduction, this paper is based on two previously published papers [1, 2]; the differences and additions with regard to those papers are detailed in the introduction.

References

  1. 1.
    J. Togelius, M. Preuss, G.N. Yannakakis, Towards multiobjective procedural map generation, in Proceedings of the FDG Workshop on Procedural Content Generation (2010)Google Scholar
  2. 2.
    J. Togelius, M. Preuss, N. Beume, S. Wessing, J. Hagelbäck, G.N. Yannakakis, Multiobjective exploration of the starcraft map space, in Proceedings of the IEEE Conference on Computational Intelligence and Games (CIG) (2010)Google Scholar
  3. 3.
    T. Adams, Re: optimization-based versus “constructive” pcg (post to the “procedural content generation” google group)Google Scholar
  4. 4.
    G.S.P. Miller, The definition and rendering of terrain maps, in Proceedings of SIGGRAPH, vol 20 (1986)Google Scholar
  5. 5.
    J. Olsen, Realtime procedural terrain generation, University of Southern Denmark, Tech. Rep. (2004)Google Scholar
  6. 6.
    J. Doran, I. Parberry, Controllable procedural terrain generation using software agents, in IEEE Transactions on Computational Intelligence and AI in Games (2010)Google Scholar
  7. 7.
    R. Smelik, T. Tutenel, K.J. de Kraker, R. Bidarra, Integrating procedural generation and manual editing of virtual worlds, in Proceedings of the FDG Workshop on Procedural Content Generation (2010)Google Scholar
  8. 8.
    J. Togelius, G.N. Yannakakis, K.O. Stanley, C. Browne, Search-based procedural content generation: a taxonomy and survey, in IEEE Transactions on Computational Intelligence and AI in Games, vol in print (2011)Google Scholar
  9. 9.
    M. Frade, F.F. de Vega, C. Cotta, Evolution of artificial terrains for video games based on accessibility, in Proceedings of the European Conference on Applications of Evolutionary Computation (EvoApplications), vol 6024 (Springer LNCS, 2010), pp. 90–99Google Scholar
  10. 10.
    N. Sorenson, P. Pasquier, Towards a generic framework for automated video game level creation, in Proceedings of the European Conference on Applications of Evolutionary Computation (EvoApplications), vol 6024 (Springer LNCS, 2010), pp. 130–139Google Scholar
  11. 11.
    D. Ashlock, T. Manikas, K. Ashenayi, Evolving a diverse collection of robot path planning problems, in Proceedings of the Congress On Evolutionary Computation (2006), pp. 6728–6735Google Scholar
  12. 12.
    J. Togelius, R. De Nardi, S.M. Lucas, Towards automatic personalised content creation in racing games, in Proceedings of the IEEE Symposium on Computational Intelligence and Games (2007)Google Scholar
  13. 13.
    C. Pedersen, J. Togelius, G.N. Yannakakis, Modeling player experience in super mario bros, in Proceedings of the IEEE Symposium on Computational Intelligence and Games (2009)Google Scholar
  14. 14.
    E. Hastings, R. Guha, K.O. Stanley, Evolving content in the galactic arms race video game, in Proceedings of the IEEE Symposium on Computational Intelligence and Games (2009)Google Scholar
  15. 15.
    J. Togelius, J. Schmidhuber, An experiment in automatic game design, in Proceedings of the IEEE Symposium on Computational Intelligence and Games (2008)Google Scholar
  16. 16.
    C. Browne, Automatic generation and evaluation of recombination games, Ph.D. dissertation, Queensland University of Technology (2008)Google Scholar
  17. 17.
    I. Das, J.E. Dennis, A closer look at drawbacks of minimizing weighted sums of objectives for pareto set generation in multicriteria optimization problems, in Structural and Multidisciplinary Optimization, vol 14 (1997), pp. 63–69Google Scholar
  18. 18.
    J. Koski, Defectiveness of weighting method in multicriterion optimization of structures, Communications in Applied Numerical Methods, vol 1 (1985), pp. 333–337Google Scholar
  19. 19.
    A. Agapitos, J. Togelius, S.M. Lucas, J. Schmidhuber, A. Konstantinides, Generating diverse opponents with multiobjective evolution, in Proceedings of the IEEE Symposium on Computational Intelligence and Games (2008)Google Scholar
  20. 20.
    N. van Hoorn, J. Togelius, D. Wierstra, J. Schmidhuber, Robust player imitation with multiobjective evolution, in Proceedings of the IEEE Symposium on Computational Intelligence and Games (CIG) (2009)Google Scholar
  21. 21.
    J. Schrum, R. Miikkulainen, Constructing complex npc behavior via multi-objective neuroevolution, in Proceedings of the Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE) (2008)Google Scholar
  22. 22.
    F.J. Gomez, J. Togelius, J. Scmidhuber, Measuring and optimizing behavioral complexity for evolutionary reinforcement learning, in Proceedings of the International Conference on Artificial Neural Networks (ICANN) (2009)Google Scholar
  23. 23.
    J. Togelius, G.N. Yannakakis, K.O. Stanley, C. Browne, Search-based procedural content generation, in Proceedings of the European Conference on Applications of Evolutionary Computation (EvoApplications), vol 6024 (Springer LNCS, 2010)Google Scholar
  24. 24.
    S. Papert, Teaching children thinking. Massachusetts Institute of Technology AI Memos, Tech. Rep. 247 (1971)Google Scholar
  25. 25.
    T.W. Malone, What makes computer games fun? Byte 6, 258–277 (1981)Google Scholar
  26. 26.
    M. Csikszentmihalyi, Flow: The Psychology of Optimal Experience (Harper & Row, New York, 1990)Google Scholar
  27. 27.
    R. Koster, Theory of Fun for Game Design (O'Reilly Media, Scottsdale, AZ, 2004), p. 256Google Scholar
  28. 28.
    K. Deb, A. Pratap, S. Agarwal, A fast and elitist multi-objective genetic algorithm: NSGA-II. IEEE Trans. Evolut. Comput. 6(2), 182–197 (2002)Google Scholar
  29. 29.
    N. Beume, B. Naujoks, M. Emmerich, SMS-EMOA: multiobjective selection based on dominated hypervolume. European Journal of Operational Research, 181(3), 1653–1669 (2007)zbMATHCrossRefGoogle Scholar
  30. 30.
    K. Deb, R.B. Agrawal, Simulated binary crossover for continuous search space. Complex Syst. 9, 115–148 (1995)MathSciNetzbMATHGoogle Scholar
  31. 31.
    M. López-Ibáñez, L. Paquete, T. Stützle, EAF graphical tools, 2010 (Online). Available: http://iridia.ulb.ac.be/manuel/eaftools
  32. 32.
    V.G. da Fonseca, C.M. Fonseca, A.O. Hall, Inferential performance assessment of stochastic optimisers and the attainment function, in EMO ’01: Proceedings of the First International Conference on Evolutionary Multi-Criterion Optimization (Springer, London, 2001), pp. 213–225Google Scholar
  33. 33.
    M. Preuss, C. Kausch, C. Bouvy, F. Henrich, Decision space diversity can be essential for solving multiobjective real-world problems, in MCDM for Sustainable Energy and Transportation Systems, EMO Track, ed. by M. Ehrgott et al. (Springer, Berlin, 2008), pp. 367–377Google Scholar
  34. 34.
    G. Rudolph, B. Naujoks, M. Preuss, Capabilities of emoa to detect and preserve equivalent pareto subsets, in Evolutionary Multi-Criterion Optimization, 4th International Conference, EMO 2007, Proceedings, ser. Lecture Notes in Computer Science, vol 4403, ed. by S. Obayashi, K. Deb, C. Poloni, T. Hiroyasu, T. Murata (Springer, 2007), pp. 36–50Google Scholar
  35. 35.
    J. Hagelbäck, M. Preuss, B. Weber, CIG 2010 StarCraft RTS AI Competition (2010), http://ls11-www.cs.tu-dortmund.de/rts-competition/starcraft-cig2010/
  36. 36.
    G.N. Yannakakis, How to model and augment player satisfaction: a review, in Proceedings of the 1st Workshop on Child, Computer and Interaction (ACM Press, Chania, Crete, 2008)Google Scholar
  37. 37.
    E. Wilson, Probable inference, the law of succession, and statistical inference. J. Am. Stat. Assoc. 22, 209–212 (1927)CrossRefGoogle Scholar
  38. 38.
    G. Smith, J. Whitehead, M. Mateas, Tanagra: reactive planning and constraint solving for mixed-initiative level design. IEEE Trans. Comput. Intell. AI Games 3(3), 201–215 (2011). doi: 10.1109/TCIAIG.2011.2159716 CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  • Julian Togelius
    • 1
  • Mike Preuss
    • 2
  • Nicola Beume
    • 2
  • Simon Wessing
    • 2
  • Johan Hagelbäck
    • 3
  • Georgios N. Yannakakis
    • 1
  • Corrado Grappiolo
    • 1
  1. 1.IT University of CopenhagenCopenhagen SDenmark
  2. 2.TU DortmundDortmundGermany
  3. 3.Blekinge Institute of TechnologyKarlskronaSweden

Personalised recommendations