Skip to main content
Springer Nature Link
Log in

Evolving Generalised Maze Solvers

  • Conference paper
  • First Online:
Applications of Evolutionary Computation (EvoApplications 2015)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 9028))

Included in the following conference series:

  • 1960 Accesses

Abstract

This paper presents a study of the efficacy of comparative controller design methods that aim to produce generalised problem solving behaviours. In this case study, the goal was to use neuro-evolution to evolve generalised maze solving behaviours. That is, evolved robot controllers that solve a broad range of mazes. To address this goal, this study compares objective, non-objective and hybrid approaches to direct the search of a neuro-evolution controller design method. The objective based approach was a fitness function, the non-objective based approach was novelty search, and the hybrid approach was a combination of both. Results indicate that, compared to the fitness function, the hybrid and novelty search evolve significantly more maze solving behaviours that generalise to larger and more difficult maze sets. Thus this research provides empirical evidence supporting novelty and hybrid novelty-objective search as approaches for potentially evolving generalised problem solvers.

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

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Goertzel, B., Pennachin, C.: Artificial General Intelligence. Springer, Heidelberg (2007)

    Book  Google Scholar 

  2. Schmidhuber, J.: Ultimate cognition à la gödel. Cogn. Comput. 1(2), 177–193 (2009)

    Article  Google Scholar 

  3. Hutter, M.: Universal Artificial Intelligence. Springer, Heidlberg (2005)

    MATH  Google Scholar 

  4. Looks, M., Goertzel, B., Pennachin, C.: Novamente: an integrative architecture for general intelligence. In: AAAI Fall Symposium, Achieving Human-Level Intelligence (2004)

    Google Scholar 

  5. Genesereth, M., Love, N., Pell, B.: General game playing: overview of the AAAI competition. AI Mag. 26(2), 62–72 (2005)

    Google Scholar 

  6. Finnsson, H., Björnsson, Y.: Simulation-based approach to general game playing. In: AAAI, vol. 8, pp. 259–264 (2008)

    Google Scholar 

  7. Floreano, D., Dürr, P., Mattiussi, C.: Neuroevolution: from architectures to learning. Evol. Intel. 1(1), 47–62 (2008)

    Article  Google Scholar 

  8. Rozin, P.: The evolution of intelligence and access to the cognitive unconscious. In: Sprague, J.M., Epstein, A.N. (eds.) Progress in Psychology, pp. 245–280. Academic Press, New York (1976)

    Google Scholar 

  9. Eiben, A., Smith, J.: Introduction to Evolutionary Computing. Springer, Heidelberg (2003)

    Book  MATH  Google Scholar 

  10. Lehman, J., Stanley, K.: Abandoning objectives: evolution through the search for novelty alone. Evol. Comput. 19(2), 189–223 (2011)

    Article  Google Scholar 

  11. Gomez, F., Miikkulainen, R.: Solving non-markovian control tasks with neuroevolution. In: IJCAI, vol. 99, pp. 1356–1361 (1999)

    Google Scholar 

  12. Gomez, F.J., Schmidhuber, J., Miikkulainen, R.: Efficient non-linear control through neuroevolution. In: Fürnkranz, J., Scheffer, T., Spiliopoulou, M. (eds.) ECML 2006. LNCS (LNAI), vol. 4212, pp. 654–662. Springer, Heidelberg (2006)

    Chapter  Google Scholar 

  13. Velez, R., Clune, J.: Novelty search creates robots with general skills for exploration. In: Proceedings of the 2014 Conference on Genetic and Evolutionary Computation, pp. 737–744. ACM (2014)

    Google Scholar 

  14. Shorten, D., Nitschke, G.: How evolvable is novelty search? (2014)

    Google Scholar 

  15. Clune, J., Beckmann, B., Ofria, C., Pennock, R.: Evolving coordinated quadruped gaits with the hyperneat generative encoding. In: IEEE Congress on Evolutionary Computation, CEC 2009, pp. 2764–2771. IEEE (2009)

    Google Scholar 

  16. Coleman, O., Blair, A., Clune, J.: Automated generation of environments to test the general learning capabilities of AI agents

    Google Scholar 

  17. Richards, N., Moriarty, D., Miikkulainen, R.: Evolving neural networks to play go. Appl. Intell. 8(1), 85–96 (1998)

    Article  Google Scholar 

  18. Yong, C., Miikkulainen, R.: Coevolution of role-based cooperation in multiagent systems. IEEE Trans. Auton. Mental Dev. 1(3), 170–186 (2009)

    Article  Google Scholar 

  19. Shorten, D., Nitschke, G.: Generational neuro-evolution: restart and retry for improvement. In: Proceedings of the 2014 Conference on Genetic and Evolutionary Computation, pp. 225–232. ACM (2014)

    Google Scholar 

  20. Koppejan, R., Whiteson, S.: Neuroevolutionary reinforcement learning for generalized helicopter control. In: Proceedings of the 11th Annual Conference on Genetic and Evolutionary Computation, pp. 145–152. ACM (2009)

    Google Scholar 

  21. Rajagopalan, P., Rawal, A., Holekamp, K., Miikkulainen, R.: General intelligence through prolonged evolution of densely connected neural networks. In: Proceedings of the 2014 Conference Companion on Genetic and Evolutionary Computation Companion, pp. 35–36. ACM (2014)

    Google Scholar 

  22. Lehman, J., Stanley, K.: Efficiently evolving programs through the search for novelty. In: Proceedings of the 12th Annual Conference on Genetic and Evolutionary Computation, pp. 837–844. ACM (2010)

    Google Scholar 

  23. Urbano, P., Georgiou, L.: Improving grammatical evolution in santa fe trail using novelty search. In: Advances in Artificial Life, ECAL, vol. 12, pp. 917–924 (2013)

    Google Scholar 

  24. Cuccu, G., Gomez, F., Glasmachers, T.: Novelty-based restarts for evolution strategies. In: 2011 IEEE Congress on Evolutionary Computation (CEC), pp. 158–163. IEEE (2011)

    Google Scholar 

  25. Lehman, J., Stanley, K.: Revising the evolutionary computation abstraction: minimal criteria novelty search. In: Proceedings of the 12th Annual Conference on Genetic and Evolutionary Computation, pp. 103–110. ACM (2010)

    Google Scholar 

  26. Gomes, J., Urbano, P., Christensen, A.L.: Progressive minimal criteria novelty search. In: Pavón, J., Duque-Méndez, N.D., Fuentes-Fernández, R. (eds.) IBERAMIA 2012. LNCS, vol. 7637, pp. 281–290. Springer, Heidelberg (2012)

    Chapter  Google Scholar 

  27. Inden, B., Jin, Y., Haschke, R., Ritter, H., Sendhoff, B.: An examination of different fitness and novelty based selection methods for the evolution of neural networks. Soft Comput. 17(5), 753–767 (2013)

    Article  Google Scholar 

  28. Kistemaker, S., Whiteson, S.: Critical factors in the performance of novelty search. In: Proceedings of the 13th Annual Conference on Genetic and Evolutionary Computation, pp. 965–972. ACM (2011)

    Google Scholar 

  29. Stanley, K., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evol. Comput. 10(2), 99–127 (2002)

    Article  Google Scholar 

  30. Stanley, K., Bryant, B., Miikkulainen, R.: Real-time neuroevolution in the nero video game. IEEE Trans. Evol. Comput. 9(6), 653–668 (2005)

    Article  Google Scholar 

  31. Xu, J., Kaplan, C.: Image-guided maze construction. ACM Trans. Graph. (TOG) 26, 29 (2007)

    Article  Google Scholar 

  32. Pullen, W.: Think labyrinth: Daedalus (2014)

    Google Scholar 

  33. Osmankovic, D., Konjicija, S.: Implementation of q learning algorithm for solving maze problem. In: MIPRO, 2011 Proceedings of the 34th International Convention, pp. 1619–1622. IEEE (2011)

    Google Scholar 

  34. Gregor, D., Troyer, M.: Boost. mpi (2006)

    Google Scholar 

  35. Flannery, B., Teukolsky, S., Vetterling, W.: Numerical Recipes. Cambridge University Press, Cambridge (1986)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science, University of Cape Town, Rondebosch, Cape Town, 7700, South Africa

    David Shorten & Geoff Nitschke

Authors
  1. David Shorten
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Geoff Nitschke
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to David Shorten .

Editor information

Editors and Affiliations

  1. Universidad de Granada, Granada, Spain

    Antonio M. Mora

  2. Politecnico di Torino, Turin, Italy

    Giovanni Squillero

Rights and permissions

Reprints and permissions

Copyright information

© 2015 Springer International Publishing Switzerland

About this paper

Cite this paper

Shorten, D., Nitschke, G. (2015). Evolving Generalised Maze Solvers. In: Mora, A., Squillero, G. (eds) Applications of Evolutionary Computation. EvoApplications 2015. Lecture Notes in Computer Science(), vol 9028. Springer, Cham. https://doi.org/10.1007/978-3-319-16549-3_63

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-16549-3_63

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-16548-6

  • Online ISBN: 978-3-319-16549-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics