Representations for search-based methods

  • Dan AshlockEmail author
  • Sebastian Risi
  • Julian Togelius
Part of the Computational Synthesis and Creative Systems book series (CSACS)


One of the key considerations in search-based PCG is how to represent the game content. There are several important tradeoffs here, including those between locality and expressivity. This chapter presents several more new and in some respects more advanced representations. These representations include several representations for dungeon levels, compositional pattern-producing networks for flowers and weapons, and a way of representing level generators themselves.


Tile Type Require Content Binary Gene Random Level Game Content 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Ashlock, D., Lee, C., McGuinness, C.: Search-based procedural generation of maze-like levels. IEEE Transactions on Computational Intelligence and AI in Games 3(3), 260–273 (2011)Google Scholar
  2. 2.
    Ashlock, D., McGuinness, C., Ashlock, W.: Representation in evolutionary computation. In: Advances in Computational Intelligence, pp. 77–97. Springer (2012)Google Scholar
  3. 3.
    Clune, J., Lipson, H.: Evolving three-dimensional objects with a generative encoding inspired by developmental biology. In: Proceedings of the European Conference on Artificial Life (2011)Google Scholar
  4. 4.
    Hastings, E., Guha, R., Stanley, K.: Evolving content in the Galactic Arms Race video game. In: Proceedings of the IEEE Symposium on Computational Intelligence and Games, pp. 241–248 (2009)Google Scholar
  5. 5.
    Hoover, A.K., Szerlip, P.A., Norton, M.E., Brindle, T.A., Merritt, Z., Stanley, K.O.: Generating a complete multipart musical composition from a single monophonic melody with functional scaffolding. In: Proceedings of the 3rd International Conference on Computational Creativity, pp. 111–118 (2012)Google Scholar
  6. 6.
    Kerssemakers, M., Tuxen, J., Togelius, J., Yannakakis, G.N.: A procedural procedural level generator generator. In: Proceedings of the IEEE Conference on Computational Intelligence and Games, pp. 335–341 (2012)Google Scholar
  7. 7.
    Risi, S., Lehman, J., D’Ambrosio, D.B., Hall, R., Stanley, K.O.: Combining search-based procedural content generation and social gaming in the Petalz video game. In: Proceedings of the Artificial Intelligence and Interactive Digital Entertainment Conference (2012)Google Scholar
  8. 8.
    Risi, S., Lehman, J., D’Ambrosio, D.B., Stanley, K.O.: Automatically categorizing procedurally generated content for collecting games. In: Proceedings of the Workshop on Procedural Content Generation in Games (2014)Google Scholar
  9. 9.
    Secretan, J., Beato, N., D’Ambrosio, D., Rodriguez, A., Campbell, A., Folsom-Kovarik, J., Stanley, K.: Picbreeder: A case study in collaborative evolutionary exploration of design space. Evolutionary Computation 19(3), 373–403 (2011)Google Scholar
  10. 10.
    Stanley, K.O.: Compositional pattern producing networks: A novel abstraction of development. Genetic Programming and Evolvable Machines 8(2), 131–162 (2007)Google Scholar
  11. 11.
    Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evolutionary Computation 10(2), 99–127 (2002)Google Scholar
  12. 12.
    Togelius, J., De Nardi, R., Lucas, S.M.: Towards automatic personalised content creation for racing games. In: Proceedings of the IEEE Symposium on Computational Intelligence and Games, pp. 252–259 (2007)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.Department of Mathematics and StatisticsUniversity of GuelphGuelphCanada
  2. 2.IT University of CopenhagenCopenhagen SDenmark
  3. 3.Department of Computer Science and EngineeringNew York UniversityBrooklynUSA

Personalised recommendations