Neurosolver Learning to Solve Towers of Hanoi Puzzles

Andrzej Bieszczad, Skyler Kuchar


Neurosolver is a neuromorphic planner and a general problem solving (GPS) system. To acquire its problem solving capability, Neurosolver uses a structure similar to the columnar organization of the cortex of the brain and a notion of place cells. The fundamental idea behind Neurosolver is to model world using a state space paradigm, and then use the model to solve problems presented as a pair of two states of the world: the current state and the desired (i.e., goal) state. Alternatively, the current state may be known (e.g., through the use of sensors), so the problem is fully expressed by stating just the goal state. Mechanically, Neurosolver works as a memory recollection system in which training samples are given as sequences of states of the subject system. Neurosolver generates a collection of interconnected nodes (inspired by cortical columns), each of which represents a single point in the problem state space, with the connections representing state transitions. A connection map between states is generated during training, and using this learned memory information, Neurosolver is able to construct a path from its current state, to the goal state for each such pair for which a transitions is possible at all. In this paper we show that Neurosolver is capable of acquiring from scratch the complete knowledge necessary to solve any puzzle for a given Towers of Hanoi configuration.


  1. Anderson, J. R., 1983. A spreading activation theory of memory. In Journal of Verbal Learning and Verbal Behavior, 22, 261-295.
  2. Bieszczad, A. and Pagurek, B., 1998. Neurosolver: Neuromorphic General Problem Solver. In Information Sciences: An International Journal 105, pp. 239-277, Elsevier North-Holland, New York, NY.
  3. Bieszczad, A., 2008. Exploring Neurosolver's Forecasting Capabilities. In Proceedings of the 28th International Symposium on Forecasting, Nice, France, June 22-25.
  4. Bieszczad A., (2011). Predicting NN5 Time Series with Neurosolver. In Madani, K., Correia, A., Rosa, A., and Filipe, J. (Eds.), Computational Intelligence: Revised and Selected Papers of the International Joint Conference IJCCI 2009 held in Funchal-Madeira, Portugal, October 2009 (Studies in Computational Intelligence). Berlin Heidelberg: Springer-Verlag, pp. 277-288.
  5. Bieszczad, A. and Bieszczad, K., (2007) Running Rats with Neurosolver-based Brains in Mazes. In Journal of Information Technology and Intelligent Computing, Vol. 1 No. 3.
  6. Bieszczad, A. and Bieszczad, K., (2006). Contextual Learning in Neurosolver. In Lecture Notes in Computer Science: Artificial Neural Networks, Springer-Verlag, Berlin, 2006, pp. 474-484.
  7. Burnod, Y., 1988. An Adaptive Neural Network: The Cerebral Cortex, Paris, France: Masson.
  8. Collins, Allan M.; Loftus, Elizabeth F., 1975. A SpreadingActivation Theory of Semantic Processing. In Psychological Review. Vol 82(6) 407-428.
  9. Deutsch, M., 1960. The Effect of Motivational Orientation Upon Trust And Suspicion. In Human Relations, 13: 123-139.
  10. Laird, J. E., Newell, A. and Rosenbloom, P. S., 1987. SOAR: An architecture for General Intelligence. In Artificial Intelligence, 33: 1--64.
  11. Markov, A. A., 2006. An Example of Statistical Investigation of the Text Eugene Onegin Concerning the Connection of Samples in Chains (translation. by David Link). In Science in Context 19.4: 591-600.
  12. Newell, A. and Simon, H. A., 1963. GPS: A program that simulates human thought. In Feigenbaum, E. A. and Feldman, J. (Eds.), Computer and Thought. New York, NJ: McGrawHill.
  13. Nillson, N. J., 1980. Principles of Artificial Intelligence, Palo Alto, CA: Tioga Publishing Company.
  14. Russell, Stuart J.; Norvig, Peter (2003), Artificial Intelligence: A Modern Approach (2nd ed.). Upper Saddle River, NJ: Prentice Hall, pp. 111-114.
  15. Stewart, B. M. and Frame, J. S., 1941. Solution to Advanced Problem 3819. In The American Mathematical Monthly Vol. 48, No. 3 (Mar., 1941), pp. 216-219.

Paper Citation

in Harvard Style

Bieszczad A. and Kuchar S. (2015). Neurosolver Learning to Solve Towers of Hanoi Puzzles . In Proceedings of the 7th International Joint Conference on Computational Intelligence - Volume 3: NCTA, (ECTA 2015) ISBN 978-989-758-157-1, pages 28-38. DOI: 10.5220/0005600000280038

in Bibtex Style

author={Andrzej Bieszczad and Skyler Kuchar},
title={Neurosolver Learning to Solve Towers of Hanoi Puzzles},
booktitle={Proceedings of the 7th International Joint Conference on Computational Intelligence - Volume 3: NCTA, (ECTA 2015)},

in EndNote Style

JO - Proceedings of the 7th International Joint Conference on Computational Intelligence - Volume 3: NCTA, (ECTA 2015)
TI - Neurosolver Learning to Solve Towers of Hanoi Puzzles
SN - 978-989-758-157-1
AU - Bieszczad A.
AU - Kuchar S.
PY - 2015
SP - 28
EP - 38
DO - 10.5220/0005600000280038