Abstract
The 3 × 3 Rubik cube represents a potential benchmark for temporal sequence learning under a discrete application domain with multiple actions. Challenging aspects of the problem domain include the large state space and a requirement to learn invariances relative to the specific colours present the latter element of the domain making it difficult to evolve individuals that learn ‘macro-moves’ relative tomultiple cube configurations. An initial study is presented in thiswork to investigate the utility ofGenetic Programming capable of layered learning and problem decomposition. The resulting solutions are tested on 5,000 test cubes, of which specific individuals are able to solve up to 350 (7 percent) cube configurations and population wide behaviours are capable of solving up to 1,200 (24 percent) of the test cube configurations. It is noted that the design options for generic fitness functions are such that users are likely to face either reward functions that are very expensive to evaluate or functions that are very deceptive. Addressing this might well imply that domain knowledge is explicitly used to decompose the task to avoid these challenges. This would augment the described generic approach currently employed for Layered learning/ problem decomposition.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Barreto, A. M. S., Augusto, D. A., and Barbosa, H. J. C. (2009). On the characteristics of sequential decision problems and their impact on Evolutionary Computation and Reinforcement learning. In Proceedings of the International Conference on Artificial Evolution, page in press.
Baum, E. B. and Durdanovic, I. (2000). Evolution of cooperative problemsolving in an artificial economy. Neural Computation, 12:2743–2775.
El-Sourani, N., Hauke, S., and Borschbach, M. (2010). An evolutionary approach for solving the Rubik’s cube incorporating exact methods. In EvoApplications Part – 1: EvoGames, volume 6024 of LNCS, pages 80–89.
Harmeling, S., Dornhge, G., Tax, F., Meinecke, F., and Muller, K. R. (2006). Fromoutliers to prototypes:Ordering data. Neurocomputing, 69(13-15):1608–1618.
Heywood, M. I. and Lichodzijewski, P. (2010). Symbiogenesis as a mechanism for building complex adaptive systems: A review. In EvoApplications: Part 1 (EvoComplex), volume 6024 of LNCS, pages 51–60.
Korf, R. (1997). Finding optimal solutions to rubik’s cube using pattern databases. In Proceedings of the Workshop on Computer Games (IJCAI), pages 21–26.
Kunkle, D. and Cooperman, G. (2007). Twenty-six moves suffice for rubik’s cube. In Proceedings of ACM International Symposium on Symbolic and Algebraic Computation, pages 235–242.
Lichodzijewski, P. and Heywood, M. I. (2007). Pareto-coevolutionary Genetic Programming for problem decomposition in multi-class classification. In Proceedings of the Genetic and Evolutionary Computation Conference, pages 464–471.
Lichodzijewski, P. and Heywood, M. I. (2008). Managing team-based problem solving with Symbiotic Bid-based Genetic Programming. In Proceedings of the Genetic and Evolutionary Computation Conference, pages 363–370.
Lichodzijewski, P. and Heywood, M. I. (2010a). Symbiosis, complexification and simplicity under gp. In Proceedings of the Genetic and Evolutionary Computation Conference. To appear.
Lichodzijewski, P. and Heywood, M.I. (2010b). A symbiotic coevolutionary framework for layered learning. In AAAI Symposium on Complex Adaptive Systems. Under review.
Oudeyer, P.Y., Kaplan, F., and V.V. Hafner, V. V. (2007). Intrinsic motivation systems for autonomous mental development. IEEE Transactions on Evolutionary Computation, 11:265–286.
Pollack, J. B. and Blair, A. D. (1998). Co-evolution in the successful learning of backgammon strategy. Machine Learning, 32:225–240.
Stone, P. (2007). Learning and multiagent reasoning for autonomous agents. In Proceedings of the International Joint Conference on Artificial Intelligence, pages 13–30.
Whiteson, S. and Stone, P. (2006). Evolutionary function approximation for reinforcement learning. Journal of Machine Learning Research, 7:887–917.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer Science+Business Media, LLC
About this chapter
Cite this chapter
Lichodzijewski, P., Heywood, M. (2011). The Rubik Cube and GP Temporal Sequence Learning: An Initial Study. In: Riolo, R., McConaghy, T., Vladislavleva, E. (eds) Genetic Programming Theory and Practice VIII. Genetic and Evolutionary Computation, vol 8. Springer, New York, NY. https://doi.org/10.1007/978-1-4419-7747-2_3
Download citation
DOI: https://doi.org/10.1007/978-1-4419-7747-2_3
Published:
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4419-7746-5
Online ISBN: 978-1-4419-7747-2
eBook Packages: Computer ScienceComputer Science (R0)