Advertisement

Search Strategies for Grammatical Optimization Problems—Alternatives to Grammar-Guided Genetic Programming

  • Gabriel KronbergerEmail author
  • Michael Kommenda
Chapter
Part of the Studies in Computational Intelligence book series (SCI, volume 595)

Abstract

In this chapter, we have a closer look at search strategies for optimization problems, where the structure of valid solutions is defined through a formal grammar. These problems frequently occur in the genetic programming (GP) literature, especially in the context of grammar-guided genetic programming [18]. Even though a lot of progress has been made to extend and improve GP in the last 25 years and many impressive solutions have been produced by GP, the initial goal of an automated programming machine for generating computer programs is still far away and GP is not yet established as a reliable and general method for solving grammatical optimization problems. Instead, many different GP variants have been described and used for solving specific problems. Today the term GP refers to a large set of related algorithms where the commonality mainly is that an evolutionary algorithm is used to produce solutions which often—but not always—represent code that can be executed by a problem specific virtual machine or an interpreter. This code is most frequently represented either as a tree or as a linear chain of instructions. The term genetic programming thus categorizes algorithms based on their approach to solution manipulation. However, the type of problems that is solved using these algorithms is more general. Especially for practitioners, it is often not relevant how a solution has been produced as only the solution itself is relevant. We argue that even though genetic programming is a powerful approach, it might not always be the optimal approach for solving “genetic programming problems” and instead other algorithms might work better for certain problems. Therefore, in this chapter we take a fresh look at those problems, that we in the following call grammatical optimization problems, and discuss various ways for solving such problems. A severely trimmed down extended abstract for this chapter appeared in [14].

Notes

Acknowledgments

The work described in this chapter has been done within the project HOPL—Heuristic Optimization in Production and Logistics and supported by the Austrian Research Promotion Agency (FFG) within the COMET programme.

References

  1. 1.
    Browne, C.B., Powley, E., Whitehouse, D., Lucas, S.M., Cowling, P.I., Rohlfshagen, P., Tavener, S., Perez, D., Samothrakis, S., Colton, S.: A survey of Monte Carlo tree search methods. IEEE Trans. Comput. Intell. AI Games 4(1), 1–43 (2012)CrossRefGoogle Scholar
  2. 2.
    Chaslot, G., De Jong, S., Saito, J.-T., Uiterwijk, J.: Monte-Carlo tree search in production management problems. In: Proceedings of the 18th BeNeLux Conference on Artificial Intelligence. pp. 91–98 (2006)Google Scholar
  3. 3.
    Coulom, R.: Efficient selectivity and backup operators in monte-carlo tree search. In: Computers and Games, pp. 72–83. Springer (2007)Google Scholar
  4. 4.
    de Mesmay, F., Rimmel, A., Voronenko, Y., Püschel, M.: Bandit-based optimization on graphs with application to library performance tuning. In: Proceedings of the 26th Annual International Conference on Machine Learning, ICML’09, pp. 729–736. ACM, New York (2009)Google Scholar
  5. 5.
    Duvenaud, D., Lloyd, J. R., Grosse, R., Tenenbaum, J.B., Ghahramani, Z.: Structure discovery in nonparametric regression through compositional kernel search (2013). arXiv preprint arXiv:1302.4922
  6. 6.
    Hasegawa, Y., Iba, H.: Latent variable model for estimation of distribution algorithm based on a probabilistic context-free grammar. IEEE Trans. Evol. Comput. 13(4), 858–878 (2009)CrossRefGoogle Scholar
  7. 7.
    Hastie, T., Tibshirani, R., Friedman, J.: The Elements of Statistical Learning, vol. 2. Springer, New York (2009)Google Scholar
  8. 8.
    Kadioglu, S., Sellmann, M.: Grammar constraints. Constraints 15(1), 117–144 (2010)CrossRefzbMATHMathSciNetGoogle Scholar
  9. 9.
    Kim, K., McKay, B.R., Punithan, D.: Sampling bias in estimation of distribution algorithms for genetic programming using prototype trees. In: PRICAI 2010: Trends in Artificial Intelligence, pp. 100–111. Springer (2010)Google Scholar
  10. 10.
    Kim, K., Shan, Y., Nguyen, X., McKay, R.: Probabilistic model building in genetic programming: a critical review. Genet. Progr. Evol. Mach. 15(2), 115–167 (2014)CrossRefGoogle Scholar
  11. 11.
    Knuth, D.: Semantics of context-free languages. Math. Syst. Theory 2(2), 127–145 (1968)CrossRefzbMATHMathSciNetGoogle Scholar
  12. 12.
    Kocsis, L., Szepesvári, C.: Bandit based Monte-Carlo planning. In: Machine Learning: ECML 2006, pp. 282–293. Springer (2006)Google Scholar
  13. 13.
    Kronberger G., Kommenda, M.: Evolution of covariance functions for Gaussian process regression using genetic programming (2013). arXiv preprint arXiv:1305.3794
  14. 14.
    Kronberger, G., Kommenda, M.: Search strategies for grammatical optimisation problems—alternatives to grammar-guided genetic programming. In: Proceedings of the 2nd Asia-Pacific Conference on Computer Aided System Engineering, APCASE 2014, 10th–12th February 2014, South Kuta, Indonesia, p. 101. APCASE Foundation (2014)Google Scholar
  15. 15.
    Kronberger, G., Kommenda, M., Wagner, S., Dobler, H.: GPDL: a framework-independent problem definition language for grammar-guided genetic programming. In: Proceeding of the Fifteenth Annual Conference Companion on Genetic and Evolutionary Computation Conference Companion, pp. 1333–1340. ACM (2013)Google Scholar
  16. 16.
    Larrañaga, P., Lozano, J.A., Estimation of Distribution Algorithms: A New Tool for Evolutionary Computation, vol. 2. Springer (2002)Google Scholar
  17. 17.
    McConaghy, T.: Ffx: fast, scalable, deterministic symbolic regression technology. In: Riolo, R., Vladislavleva, E., Moore, J.H. (eds.) Genetic Programming Theory and Practice IX, Genetic and Evolutionary Computation, pp. 235–260. Springer, New York (2011)Google Scholar
  18. 18.
    McKay, R.I., Hoai, N.X., Whigham, P.A., Shan, Y., O’Neill, M.: Grammar-based genetic programming: a survey. Genet. program. Evol. Mach. 11(3/4), 365–396 (2010)CrossRefGoogle Scholar
  19. 19.
    O’Neill, M., Ryan, C.: Grammatical Evolution: Evolutionary Automatic Programming in an Arbitrary Language, vol. 4. Springer (2003)Google Scholar
  20. 20.
    O’Neill, M., Ryan, C., Keijzer, M., Cattolico, M.: Crossover in grammatical evolution. Genet. program. Evol. Mach. 4(1), 67–93 (2003)CrossRefzbMATHGoogle Scholar
  21. 21.
    Poli, R., Langdon, W.: Foundations of Genetic Programming, vol. 103, p. 107. Springer, New York (2002)Google Scholar
  22. 22.
    Sastry, K., Goldberg, D.: Probabilistic model building and competent genetic programming. In: Riolo, R., Worzel, B. (eds.) Genetic Programming Theory and Practice. Genetic Programming Series, vol. 6, pp. 205–220. Springer (2003)Google Scholar
  23. 23.
    Sellmann, M.: The theory of grammar constraints. In: Benhamou, F. (ed.) Principles and Practice of Constraint Programming—CP 2006. Lecture Notes in Computer Science, vol. 4204, pp. 530–544. Springer, Berlin (2006)CrossRefGoogle Scholar
  24. 24.
    Shan, Y., McKay, R.I., Essam, D., Abbass, H.A.: A survey of probabilistic model building genetic programming. In: Scalable Optimization via Probabilistic Modeling, pp. 121–160. Springer (2006)Google Scholar
  25. 25.
    Worm, T., Chiu, K.: Prioritized grammar enumeration: symbolic regression by dynamic programming. In: Proceeding of the Fifteenth Annual Conference on Genetic and Evolutionary Computation Conference, pp. 1021–1028. ACM (2013)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.University of Applied Sciences Upper Austria School of Informatics, Communications and MediaHagenbergAustria

Personalised recommendations