Skip to main content
SpringerLink
Log in
Book cover

Transactions on Computational Collective Intelligence XX pp 224–258Cite as

A Question of Balance

The Benefits of Pattern-Recognition When Solving Problems in a Complex Domain

  • Chapter
  • First Online:

Part of the book series: Lecture Notes in Computer Science ((TCCI,volume 9420))

Abstract

The dual-process theory of human cognition proposes the existence of two systems for decision-making: a slower, deliberative, problem-solving system and a quicker, reactive, pattern-recognition system. We alter the balance of these systems in a number of computational simulations using three types of agent equipped with a novel, hybrid, human-like cognitive architecture. These agents are situated in the stochastic, multi-agent Tileworld domain, whose complexity can be precisely controlled and widely varied. We explore how agent performance is affected by different balances of problem-solving and pattern-recognition, and conduct a sensitivity analysis upon key pattern-recognition system variables. Results indicate that pattern-recognition improves agent performance by as much as 36.5 % and, if a balance is struck with particular pattern-recognition components to promote pattern-recognition use, performance can be further improved by up to 3.6 %. This research is of interest for studies of expert behaviour in particular, and AI in general.

This is a preview of subscription content, 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

Learn about institutional subscriptions

Notes

  1. 1.

    With respect to both the number of positions and the amount of information within each position.

  2. 2.

    See [28] for a detailed comparison of ACT-R and CHREST’s LTM implementation.

  3. 3.

    South and west are represented by negative numbers.

  4. 4.

    See [18, 26] for further details of these mechanisms.

  5. 5.

    A square in Tileworld can only contain one item (see Sect. 2), one item-on-square pattern encodes one item and the agent doesn’t encode its own location.

  6. 6.

    Due to an error in the simulation code used in a previous version of this paper [27], the results reported in this section consistently differ from those reported in the corresponding section of [27] by a factor of 10. The results reported in this section use a rectified version of the simulation code and are correct.

  7. 7.

    All F and p values for the effects discussed are equal to those outlined for average frequency of pattern-recognition system use.

References

  1. Aarts, H., Dijksterhuis, A.: Habit as knowledge structures: automaticity in goal-directed behavior. J. Pers. Soc. Psychol. 78(1), 53–63 (2000)

    Article  Google Scholar 

  2. Anderson, J.R., Bothell, D., Byrne, M.D., Douglass, S., Lebière, C., Qin, Y.L.: An integrated theory of the mind. Psychol. Rev. 111(4), 1036–1060 (2004)

    Article  Google Scholar 

  3. Arai, S., Sycara, K.: Effective learning approach for planning and scheduling in multi-agent domain. In: Meyer, J.A., Berthoz, A., Floreano, D., Roitblat, H., Wilson, S.W. (eds.) From Animals to Animats 6: Proceedings of the 6th International Conference on Simulation of Adaptive Behavior, pp. 507–516. MIT Press (2000)

    Google Scholar 

  4. Arai, S., Sycara, K.P., Payne, T.R.: Experience-based reinforcement learning to acquire effective behavior in a multi-agent domain. In: Proceedings of the 6th Pacific Rim International Conference on Artificial Intelligence, pp. 125–135 (2000)

    Google Scholar 

  5. Baker, J.E.: Reducing bias and inefficiency in the selection algorithm. In: Grefenstette, J.J. (ed.) Proceedings of the 2nd International Conference on Genetic Algorithms on Genetic Algorithms and Their Application. L. Erlbaum Associates Inc. (1987)

    Google Scholar 

  6. Bilalić, M., McLeod, P., Gobet, F.: Inflexibility of experts - reality or myth? Quantifying the Einstellung effect in chess masters. Cogn. Psychol. 56(2), 73–102 (2008)

    Article  Google Scholar 

  7. Bossomaier, T., Traish, J., Gobet, F., Lane, P.C.R.: Neuro-cognitive model of move location in the game of Go. In: Proceedings of the 2012 International Joint Conference on Neural Networks (2012)

    Google Scholar 

  8. Chase, W.G., Simon, H.A.: Perception in chess. Cogn. Psychol. 4, 55–81 (1973)

    Article  Google Scholar 

  9. Dayan, P., Daw, N.D.: Decision theory, reinforcement learning, and the brain. Cogn. Affect. Behav. Neurosci. 8(4), 429–453 (2008)

    Article  Google Scholar 

  10. de Groot, A.D.: Thought and Choice in Chess (First edition in 1946). Mouton, The Hague (1978)

    Google Scholar 

  11. de Groot, A.D., Gobet, F.: Perception and Memory in Chess: Heuristics of the Professional Eye. Van Gorcum, Assen (1996)

    Google Scholar 

  12. Erev, I., Roth, A.E.: Predicting how people play games: reinforcement learning in experimental games with unique, mixed strategy equilibria. Am. Econ. Rev. 88(4), 848–881 (1998)

    Google Scholar 

  13. Evans, J.S.B.T.: Dual-processing accounts of reasoning, judgment and social cognition. Annu. Rev. Psychol. 59, 255–278 (2008)

    Article  Google Scholar 

  14. Freudenthal, D., Pine, J.M., Gobet, F.: Simulating the referential properties of Dutch, German and English root infinitives in MOSAIC. Lang. Learn. Dev. 15, 1–29 (2009)

    Article  Google Scholar 

  15. Gillan, C.M., Papmeyer, M., Morein-Zamir, S., Sahakian, B.J., Fineberg, N.A., Robbins, T.W., de Wit, S.: Disruption in the balance between goal-directed behavior and habit learning in obsessive-compulsive disorder. Am. J. Psychiatry 168, 718–726 (2011)

    Article  Google Scholar 

  16. Gobet, F.: Les mémoires d’un joueur d’échecs. Editions Universitaires, Fribourg, Switzerland (1993)

    Google Scholar 

  17. Gobet, F.: A pattern-recognition theory of search in expert problem solving. Thinking Reasoning 3, 291–313 (1997)

    Article  Google Scholar 

  18. Gobet, F., Lane, P.C.R., Croker, S.J., Cheng, P.C.H., Jones, G., Oliver, I., Pine, J.M.: Chunking mechanisms in human learning. Trends Cogn. Sci. 5, 236–243 (2001)

    Article  Google Scholar 

  19. Grefenstette, J.J.: Credit assignment in rule discovery systems based on genetic algorithms. Mach. Learn. 3, 225–245 (1988)

    Google Scholar 

  20. Hesketh, B.: Dilemmas in training for transfer and retention. Appl. Psychol. 46(4), 317–339 (1997)

    Google Scholar 

  21. Holroyd, C.B., Coles, M.G.: The neural basis of human error processing: reinforcement learning, dopamine, and the error-related negativity. Psychol. Rev. 109(4), 679–709 (2002)

    Article  Google Scholar 

  22. Jones, G.A., Gobet, F., Pine, J.M.: Linking working memory and long-term memory: a computational model of the learning of new words. Dev. Sci. 10, 853–873 (2007)

    Article  Google Scholar 

  23. Jongman, R.W.: Het Oog Van De Meester. Van Gorcum, Assen (1968)

    Google Scholar 

  24. Kheirbek, M.A., Klemenhagen, K.C., Sahay, A., Hen, R.: Neurogenesis and generalization: a new approach to stratify and treat anxiety disorders. Nat. Neurosci. 15(12), 1613–1620 (2012)

    Article  Google Scholar 

  25. Laird, J.E.: The Soar Cognitive Architecture. MIT Press, Cambridge (2012)

    Google Scholar 

  26. Lane, P.C.R., Gobet, F.: CHREST models of implicit learning and board game interpetation. In: Bach, J., Goertzel, B., Ikle, M. (eds.) Proceedings of the 5th Conference on Artificial General Intelligence. LNAI, vol. 7716, pp. 148–157. Springer, Heidelberg (2012)

    Chapter  Google Scholar 

  27. Lloyd-Kelly, M., Gobet, F., Lane, P.C.R.: The art of balance: problem-solving vs. pattern-recognition. In: Proceedings of the 7th International Conference on Agents and Artificial Intelligence, pp. 131–142 (2015)

    Google Scholar 

  28. Lloyd-Kelly, M., Gobet, F., Lane, P.C.R.: Piece of mind: long-term memory structure in ACT-R and CHREST. In: Noelle, D.C., Dale, R., Warlaumont, A.S., Yoshimi, J., Matlock, T., Jennings, C.D., Maglio, P.P. (eds.) Proceedings of the 37th Annual Meeting of the Cognitive Science Society, pp. 1422–1427. Cognitive Science Society (2015)

    Google Scholar 

  29. Lloyd-Kelly, M., Lane, P.C.R., Gobet, F.: The effects of bounding rationality on the performance and learning of CHREST agents in Tileworld. In: Bramer, M., Petridis, M. (eds.) Research and Development in Intelligent Systems XXXI, pp. 149–162. Springer International Publishing, Switzerland (2014)

    Google Scholar 

  30. Luchins, A.S.: Mechanization in problem solving: the effect of Einstellung. Psychol. Monogr. 54(6), 1–95 (1942)

    Article  Google Scholar 

  31. Miller, G.A.: The magical number seven, plus or minus two: some limits on our capacity for processing information. Psychol. Rev. 63, 81–97 (1956)

    Article  Google Scholar 

  32. Miyazaki, K., Yamamura, M., Kobayashi, S.: On the rationality of profit sharing in reinforcement learning. In: 3rd International Conference on Fuzzy Logic, Neural Nets and Soft Computing, pp. 285–288. Korean Institute of Intelligent Systems (1994)

    Google Scholar 

  33. Pollack, M., Ringuette, M.: Introducing the Tileworld: experimentally evaluating agent architectures. In: 8th National Conference on Artificial Intelligence, pp. 183–189. AAAI Press (1990)

    Google Scholar 

  34. Raza, M., Sastry, V.: Variability in behavior of command agents with human-like decision making strategies. In: 10th International Conference on Computer Modelling and Simulation, pp. 562–567 (2008)

    Google Scholar 

  35. Saariluoma, P.: Error in chess: the apperception-restructuring view. Psychol. Res. 54, 17–26 (1992)

    Article  Google Scholar 

  36. Samsonovich, A.: Toward a unified catalog of implemented cognitive architectures. In: Proceedings of the 2010 Conference on Biologically Inspired Cognitive Architectures, pp. 195–244. IOS Press, Amsterdam, The Netherlands (2010)

    Google Scholar 

  37. Simari, G.I., Parsons, S.D.: On approximating the best decision for an autonomous agent. In: 6th Workshop on Game Theoretic and Decision Theoretic Agents, pp. 91–100. Third Conference on Autonomous Agents and Multi-agent Systems (2004)

    Google Scholar 

  38. Simon, H.A.: The Sciences of the Artificial. MIT Press, Cambridge (1969)

    Google Scholar 

  39. Simonton, D.K.: Origins of Genius: Darwinian Perspectives on Creativity. Oxford University Press, New York (1999)

    Google Scholar 

  40. Sloman, S.: The empirical case for two systems of reasoning. Psychol. Bull. 119, 3–22 (1996)

    Article  Google Scholar 

  41. Sternberg, R.J.: Costs of expertise. In: The Road to Excellence: The Acquisition of Expert Performance in the Arts and Sciences, Sports, and Games, pp. 347–354. Lawrence Erlbaum Associates, Hillsdale, NJ (1996)

    Google Scholar 

  42. Sun, R., Merrill, E., Peterson, T.: From implicit skills to explicit knowledge: a bottom-up model of skill learning. Cogn. Sci. 25, 203–244 (2001)

    Article  Google Scholar 

  43. Sun, R., Slusarz, P., Terry, C.: The interaction of the explicit and the implicit in skill learning: a dual-process approach. Psychol. Rev. 112(1), 159–192 (2005)

    Article  Google Scholar 

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

    Google Scholar 

  45. Watkins, C.J.C.H., Dayan, P.: Technical note: Q-learning. Mach. Learn. 8, 279–292 (1992)

    MATH  Google Scholar 

  46. de Wit, S., Dickinson, A.: Associative theories of goal-directed behaviour: a case for animal-human translational models. Psychol. Res. 73(4), 463–476 (2009)

    Article  Google Scholar 

  47. Zeitz, C.M.: Some concrete advantages of abstraction: how experts’ representations facilitate reasoning. In: Expertise in Context: Human and Machine, pp. 43–65. The MIT Press, Cambridge, MA (1997)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Psychological Sciences, University of Liverpool, Liverpool, L69 3BX, UK

    Martyn Lloyd-Kelly & Fernand Gobet

  2. School of Computer Science, University of Hertfordshire, Hertfordshire, AL10 9AB, UK

    Peter C. R. Lane

Authors
  1. Martyn Lloyd-Kelly
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Fernand Gobet
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Peter C. R. Lane
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Martyn Lloyd-Kelly .

Editor information

Editors and Affiliations

  1. Faculty of Computer Science and Manageme, Wroclaw University of Technology, Wroclaw, Poland

    Ngoc Thanh Nguyen

  2. Swinburne University of Technology, Hawthorn, Australia

    Ryszard Kowalczyk

  3. LERIA - UFR Sciences, Angers Cedex 01, France

    Béatrice Duval

  4. Leiden, Zuid-Holland, Leiden University, Leiden, The Netherlands

    Jaap van den Herik

  5. LERIA - UFR Sciences, Angers Cedex 01, France

    Stephane Loiseau

  6. INSTICC, Polytechnic Institute of Setubal, Setubal, Portugal

    Joaquim Filipe

Rights and permissions

Reprints and permissions

Copyright information

© 2015 Springer-Verlag Berlin Heidelberg

About this chapter

Cite this chapter

Lloyd-Kelly, M., Gobet, F., Lane, P.C.R. (2015). A Question of Balance. In: Nguyen, N., Kowalczyk, R., Duval, B., van den Herik, J., Loiseau, S., Filipe, J. (eds) Transactions on Computational Collective Intelligence XX . Lecture Notes in Computer Science(), vol 9420. Springer, Cham. https://doi.org/10.1007/978-3-319-27543-7_11

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-27543-7_11

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-27542-0

  • Online ISBN: 978-3-319-27543-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation