The Art of Balance - Problem-Solving vs. Pattern-Recognition

Martyn Lloyd-Kelly, Fernand Gobet, Peter C. R. Lane

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. The aim of this work is to explore the effect on agent performance of altering the balance of these systems in an environment of varying complexity. This is an important question, both in the realm of explanations of expert behaviour and to AI in general. To achieve this, we implement three distinct types of agent, embodying different balances of their problem-solving and pattern-recognition systems, using a novel, hybrid, human-like cognitive architecture. These agents are then situated in the virtual, stochastic, multi-agent ``Tileworld'' domain, whose intrinsic and extrinsic environmental complexity can be precisely controlled and widely varied. This domain provides an adequate test-bed to analyse the research question posed. A number of computational simulations are run. Our results indicate that there is a definite performance benefit for agents which use a mixture of problem-solving and pattern-recognition systems, especially in highly complex environments.

References

  1. Aarts, H. and Dijksterhuis, A. (2000). Habit as knowledge structures: Automaticity in goal-directed behavior. Journal of Personality and Social Psychology, 78(1):53-63.
  2. Arai, S., Sycara, K. P., and Payne, T. R. (2000). Experiencebased reinforcement learning to acquire effective behavior in a multi-agent domain. In Proceedings of the 6th Pacific Rim International Conference on Artificial Intelligence, pages 125-135.
  3. Baker, J. E. (1987). Reducing bias and inefficiency in the selection algorithm. In Grefenstette, J. J., editor, Proceedings of the Second International Conference on Genetic Algorithms on Genetic Algorithms and Their Application. L. Erlbaum Associates Inc.
  4. Bilalic, M., McLeod, P., and Gobet, F. (2008). Inflexibility of experts - reality or myth? Quantifying the Einstellung effect in chess masters. Cognitive Psychology, 56(2):73-102.
  5. Bratman, M. E. (1987). Intentions, Plans, and Practical Reason. Harvard University Press.
  6. Chase, W. G. and Simon, H. A. (1973). Perception in chess. Cognitive Psychology, 4:55-81.
  7. Dayan, P. and Daw, N. D. (2008). Decision theory, reinforcement learning, and the brain. Cognitive, Affective and Behavioral Neuroscience, 8(4):429-453.
  8. de Groot, A. D. (1978). Thought and Choice in Chess (First edition in 1946). Mouton, The Hague.
  9. de Groot, A. D. and Gobet, F. (1996). Perception and Memory in Chess: Heuristics of the Professional Eye. Van Gorcum, Assen.
  10. de Wit, S. and Dickinson, A. (2009). Associative theories of goal-directed behaviour: a case for animalhuman translational models. Psychological Research, 73(4):463-476.
  11. Erev, I. and Roth, A. E. (1998). Predicting how people play games: Reinforcement learning in experimental games with unique, mixed strategy equilibria. The American Economic Review, 88(4):pp. 848-881.
  12. Evans, J. S. B. T. (2008). Dual-processing accounts of reasoning, judgment and social cognition. Annual Review of Psychology, 59:255-278.
  13. Freudenthal, D., Pine, J. M., and Gobet, F. (2009). Simulating the referential properties of Dutch, German and English root infinitives in MOSAIC. Language Learning and Development, 15:1-29.
  14. Gillan, C. M., Papmeyer, M., Morein-Zamir, S., Sahakian, B. J., Fineberg, N. A., Robbins, T. W., and de Wit, S. (2011). Disruption in the balance between goaldirected behavior and habit learning in obsessivecompulsive disorder. American Journal of Psychiatry.
  15. Gobet, F. (1993). Les mémoires d'un joueur d'échecs. Editions Universitaires, Fribourg, Switzerland.
  16. Gobet, F. (1997). A pattern-recognition theory of search in expert problem solving. Thinking and Reasoning, 3:291-313.
  17. Gobet, F., Lane, P. C. R., Croker, S. J., Cheng, P. C.-H., Jones, G., Oliver, I., and Pine, J. M. (2001). Chunking mechanisms in human learning. Trends in Cognitive Sciences, 5:236-243.
  18. Gobet, F. and Simon, H. A. (2000). Five seconds or sixty? Presentation time in expert memory. Cognitive Science, 24:651-82.
  19. Grefenstette, J. J. (1988). Credit assignment in rule discovery systems based on genetic algorithms. Machine Learning, 3:225-245.
  20. Hesketh, B. (1997). Dilemmas in training for transfer and retention. Applied Psychology, 46(4):317-339.
  21. Holroyd, C. B. and Coles, M. G. (2002). The neural basis of human error processing: Reinforcement learning, dopamine, and the error-related negativity. Psychological Review, 109(4):679-709.
  22. Jongman, R. W. (1968). Het Oog Van De Meester. Assen: Van Gorcum.
  23. Laird, J. E. (2012). The Soar Cognitive Architecture. MIT Press.
  24. Lane, P. C. R. and Gobet, F. (2012). CHREST models of implicit learning and board game interpetation. In Bach, J., Goertzel, B., and Ikle, M., editors, Proceedings of the Fifth Conference on Artificial General Intelligence, volume LNAI 7716, pages 148-157, Berlin, Heidelberg. Springer-Verlag.
  25. Luchins, A. S. (1942). Mechanization in problem solving: The effect of einstellung. Psychological Monographs, 54(6):i-95.
  26. Miyazaki, K., Yamamura, M., and Kobayashi, S. (1994). On the rationality of profit sharing in reinforcement learning. In 3rd International Conference on Fuzzy Logic, Neural Nets and Soft Computing, pages 285- 288. Korean Institute of Intelligent Systems.
  27. Pollack, M. and Ringuette, M. (1990). Introducing the Tileworld: Experimentally evaluating agent architectures. In Eighth National Conference on Artificial Intelligence, pages 183-189. AAAI Press.
  28. Raza, M. and Sastry, V. (2008). Variability in behavior of command agents with human-like decision making strategies. In Tenth International Conference on Computer Modelling and Simulation, pages 562-567.
  29. Saariluoma, P. (1994). Location coding in chess. The Quarterly Journal of Experimental Psychology, 47A:607- 630.
  30. Samsonovich, A. (2010). Toward a unified catalog of implemented cognitive architectures. In Proceedings of the 2010 Conference on Biologically Inspired Cognitive Architectures, pages 195-244, Amsterdam, The Netherlands. IOS Press.
  31. Simari, G. I. and Parsons, S. D. (2004). On approximating the best decision for an autonomous agent. In Sixth Workshop on Game Theoretic and Decision Theoretic Agents, Third Conference on Autonomous Agents and Multi-agent Systems, pages 91-100.
  32. Simon, H. A. (1969). The sciences of the artificial. MIT Press, Cambridge, MA.
  33. Simonton, D. K. (1999). Origins of genius: Darwinian perspectives on creativity. Oxford University Press, New York.
  34. Sloman, S. (1996). The empirical case for two systems of reasoning. Psychological Bulletin, 119:3-22.
  35. Sternberg, R. J. (1996). The road to excellence: The acquisition of expert performance in the arts and sciences, sports, and games, chapter Costs of expertise, pages 347-354. Hillsdale, NJ: Lawrence Erlbaum Associates.
  36. Sun, R., Slusarz, P., and Terry, C. (2005). The interaction of the explicit and the implicit in skill learning: A dualprocess approach. Psychological Review, 112(1):159- 192.
  37. Sutton, R. S. and Barto, A. G. (1998). Reinforcement Learning: an Introduction. MIT Press.
  38. Tversky, A. and Kahneman, D. (1983). Extensional versus intuitive reasoning: The conjunction fallacy in probability judgment. Psychological Review, 90(4):293- 315.
  39. Zeitz, C. M. (1997). Expertise in context: Human and machine, chapter Some concrete advantages of abstraction: How experts' representations facilitate reasoning, pages 43-65. Cambridge, MA: The MIT Press.
Download


Paper Citation


in Harvard Style

Lloyd-Kelly M., Gobet F. and C. R. Lane P. (2015). The Art of Balance - Problem-Solving vs. Pattern-Recognition . In Proceedings of the International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-074-1, pages 131-142. DOI: 10.5220/0005215901310142


in Bibtex Style

@conference{icaart15,
author={Martyn Lloyd-Kelly and Fernand Gobet and Peter C. R. Lane},
title={The Art of Balance - Problem-Solving vs. Pattern-Recognition},
booktitle={Proceedings of the International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2015},
pages={131-142},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005215901310142},
isbn={978-989-758-074-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - The Art of Balance - Problem-Solving vs. Pattern-Recognition
SN - 978-989-758-074-1
AU - Lloyd-Kelly M.
AU - Gobet F.
AU - C. R. Lane P.
PY - 2015
SP - 131
EP - 142
DO - 10.5220/0005215901310142