Skip to main content
SpringerLink
Log in

Stepwise Evolutionary Learning Using Deep Learned Guidance Functions

  • Conference paper
  • First Online:
Artificial Intelligence XXXVI (SGAI 2019)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 11927))

Abstract

This paper explores how Learned Guidance Functions (LGFs)—a pre-training method used to smooth search landscapes—can be used as a fitness function for evolutionary algorithms. A new form of LGF is introduced, based on deep neural network learning, and it is shown how this can be used as a fitness function. This is applied to a test problem: unscrambling the Rubik’s Cube. Comparisons are made with a previous LGF approach based on random forests, and with a baseline approach based on traditional error-based fitness.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Keras: The python deep learning library. http://keras.io/. Accessed Jan 2019

  2. scikit-learn: Machine learning in python. http://scikit-learn.org/. Accessed Jan 2019

  3. Tensorflow: An open source machine learning framework for everyone. http://www.tensorflow.org/. Accessed Jan 2019

  4. Asselmeyer, T., Ebeling, W., Rosé, H.: Smoothing representation of fitness landscapes — the genotype-phenotype map of evolution. Biosystems 39(1), 63–76 (1996)

    Article  Google Scholar 

  5. Bojarski, M., et al.: End to end learning for self-driving cars. CoRR abs/1604.07316 (2016). http://arxiv.org/abs/1604.07316

  6. Culberson, J., Schaeffer, J.: Pattern databases. Comput. Intell. 14(3), 318–334 (1998)

    Article  MathSciNet  Google Scholar 

  7. Dobson, C.M.: Protein folding and misfolding. Nature 426, 884–890 (2003)

    Article  Google Scholar 

  8. Erez, T., Smart, W.D.: What does shaping mean for computational reinforcement learning? In: 2008 7th IEEE International Conference on Development and Learning, pp. 215–219 (2008)

    Google Scholar 

  9. Glover, F., Greenberg, H.: New approaches for heuristic search: a bilateral linkage with artificial intelligence. Eur. J. Oper. Res. 39(2), 119–130 (1989)

    Article  MathSciNet  Google Scholar 

  10. Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2017)

    MATH  Google Scholar 

  11. Grefenstette, J.: Optimization of control parameters for genetic algorithms. IEEE Trans. Syst. Man Cybern. 16, 122–128 (1986)

    Article  Google Scholar 

  12. Hopgood, A.A., Mierzejewska, A.: Transform ranking: a new method of fitness scaling in genetic algorithms. In: Bramer, M., Petridis, M., Coenen, F. (eds.) SGAI 2008, pp. 349–354. Springer, London (2009). https://doi.org/10.1007/978-1-84882-171-2_26

    Chapter  Google Scholar 

  13. Hutter, F., Kotthoff, L., Vanschoren, J.: AutoML: Methods, Systems, Challenges (2019). Book in preparation. Current draft at https://www.automl.org/book/. Accessed July 2019

  14. Johnson, C.G.: Solving the Rubik’s Cube with learned guidance functions. In: Proceedings of the 2018 IEEE Symposium Series in Computational Intelligence. IEEE Press (2018)

    Google Scholar 

  15. Krawiec, K.: Behavioural Program Synthesis with Genetic Programming. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-27565-9

    Book  Google Scholar 

  16. Krawiec, K., Swan, J., O’Reilly, U.M.: Behavioral program synthesis: insights and prospects. In: Riolo, R., Worzel, W., Kotanchek, M., Kordon, A. (eds.) Genetic Programming Theory and Practice XIII. GEVO, pp. 169–183. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-34223-8_10

    Chapter  Google Scholar 

  17. Kreinovich, V., Quintana, C., Fuentes, O.: Genetic algorithms: what fitness scaling is optimal? Cybern. Syst. 24, 9–26 (1993)

    Article  MathSciNet  Google Scholar 

  18. Kulis, B.: Metric learning: a survey. Found. Trends® Mach. Learn. 5(4), 287–364 (2013). https://doi.org/10.1561/2200000019

    Article  MathSciNet  MATH  Google Scholar 

  19. McAleer, S., Agostinelli, F., Shmakov, A., Baldi, P.: Solving the Rubik’s Cube Without Human Knowledge. ArXiv e-prints, May 2018

    Google Scholar 

  20. Samadi, M., Felner, A., Schaeffer, J.: Learning from multiple heuristics. In: Proceedings of Association for the Advancement of Artificial Intelligence (AAAI-08), pp. 357–362 (2008)

    Google Scholar 

  21. Moraglio, A., Krawiec, K., Johnson, C.G.: Geometric semantic genetic programming. In: Coello, C.A.C., Cutello, V., Deb, K., Forrest, S., Nicosia, G., Pavone, M. (eds.) PPSN 2012, Part I. LNCS, vol. 7491, pp. 21–31. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-32937-1_3

    Chapter  Google Scholar 

  22. Silver, D., et al.: Mastering the game of go without human knowledge. Nature 550(7676), 354–359 (2017). https://doi.org/10.1038/nature24270

    Article  Google Scholar 

  23. Singmaster, D.: Notes on Rubik’s Magic Cube. Enslow Publishing, Hillside (1981)

    Google Scholar 

  24. Slocum, J., et al.: The Cube: The Ultimate Guide to the World’s Best-Selling Puzzle. Black Dog and Leventhal, New York (2011)

    Google Scholar 

  25. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)

    MathSciNet  MATH  Google Scholar 

  26. Sturtevant, N.R., Felner, A., Barrer, M., Schaeffer, J., Burch, N.: Memory-based heuristics for explicit state spaces. In: Proceedings of the 21st International Joint Conference on Artifical Intelligence, IJCAI 2009, pp. 609–614, Morgan Kaufmann Publishers Inc. (2009)

    Google Scholar 

  27. Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)

    MATH  Google Scholar 

  28. Szubert, M., Jaśkowski, W., Liskowski, P., Krawiec, K.: Shaping fitness function for evolutionary learning of game strategies. In: Proceedings of the 15th Annual Conference on Genetic and Evolutionary Computation, pp. 1149–1156. ACM (2013)

    Google Scholar 

  29. Vanneschi, L., Castelli, M., Manzoni, L., Silva, S.: A new implementation of geometric semantic GP and its application to problems in pharmacokinetics. In: Krawiec, K., Moraglio, A., Hu, T., Etaner-Uyar, A.Ş., Hu, B. (eds.) EuroGP 2013. LNCS, vol. 7831, pp. 205–216. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-37207-0_18

    Chapter  Google Scholar 

  30. Ware, J.M., Wilson, I.D., Ware, J.A.: A Knowledge based genetic algorithm approach to automating cartographic generalisation. In: Macintosh, A., Ellis, R., Coenen, F. (eds.) Applications and Innovations in Intelligent Systems X, pp. 33–49. Springer, London (2003). https://doi.org/10.1007/978-1-4471-0649-4_3

    Chapter  Google Scholar 

  31. Widera, P., Garibaldi, J.M., Krasnogor, N.: GP challenge: evolving energy function for protein structure prediction. Genet. Program. Evolvable Mach. 11(1), 61–88 (2010)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Computing, University of Kent, Canterbury, Kent, UK

    Colin G. Johnson

  2. IASH, University of Edinburgh, Edinburgh, UK

    Colin G. Johnson

Authors
  1. Colin G. Johnson
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Colin G. Johnson .

Editor information

Editors and Affiliations

  1. University of Portsmouth, Portsmouth, UK

    Max Bramer

  2. Middlesex University, London, UK

    Miltos Petridis

Rights and permissions

Reprints and permissions

Copyright information

© 2019 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Johnson, C.G. (2019). Stepwise Evolutionary Learning Using Deep Learned Guidance Functions. In: Bramer, M., Petridis, M. (eds) Artificial Intelligence XXXVI. SGAI 2019. Lecture Notes in Computer Science(), vol 11927. Springer, Cham. https://doi.org/10.1007/978-3-030-34885-4_4

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-34885-4_4

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-34884-7

  • Online ISBN: 978-3-030-34885-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation