Abstract
Creating agents that proficiently interact with people is critical for many applications. Towards creating these agents, models are needed that effectively predict people’s decisions in a variety of problems. To date, two approaches have been suggested to generally describe people’s decision behavior. One approach creates a-priori predictions about people’s behavior, either based on theoretical rational behavior or based on psychological models, including bounded rationality. A second type of approach focuses on creating models based exclusively on observations of people’s behavior. At the forefront of these types of methods are various machine learning algorithms.This paper explores how these two approaches can be compared and combined in different types of domains. In relatively simple domains, both psychological models and machine learning yield clear prediction models with nearly identical results. In more complex domains, the exact action predicted by psychological models is not even clear, and machine learning models are even less accurate. Nonetheless, we present a novel approach of creating hybrid methods that incorporate features from psychological models in conjunction with machine learning in order to create significantly improved models for predicting people’s decisions. To demonstrate these claims, we present an overview of previous and new results, taken from representative domains ranging from a relatively simple optimization problem and complex domains such as negotiation and coordination without communication.
Similar content being viewed by others
References
Azaria, A., Rabinovich, Z., Kraus, S., Goldman, C. V., & Tsimhoni, O. (2012). Giving advice to people in path selection problems. In AAMAS (pp. 459–466).
Bengio, Y., Delalleau, O., & Roux, N. L. (2005). The curse of dimensionality for local kernel machines (Tech. Rep.).
Chalamish, M., Sarne, D., & Kraus, S. (2008). Programming agents as a means of capturing self-strategy. In AAMAS’08 (pp. 1161–1168).
Cheng, K.-L., Zuckerman, I., Nau, D. S., & Golbeck, J. (2011). The life game: Cognitive strategies for repeated stochastic games. In SocialCom/PASSATIEEE (pp. 95–102).
Evangelista, P. F., Embrechts, M. J., & Szymanski, B. K. (2006). Taming the curse of dimensionality in kernels and novelty detection. In Abraham A., B. de Bacts, M. Köppen, & B. Nickolay (Eds.), Applied soft computing technologies: The challenge of complexity (pp. 431–444). Heidelberg: Springer.
Fancher, P., & Bareket, Z. (1996). A comparison of manual versus automatic control of headway as a function of driver characteristics. 3rd Annual World Congress on Intelligent Transport Systems.
Gal Y., Grosz B., Kraus S., Pfeffer A., Shieber S. (2010) Agent decision-making in open mixed networks. Artificial Intelligence 174(18): 1460–1480
Gigerenzer G., Goldstein G. D. (1996) Reasoning the fast and frugal way: models of bounded rationality. Psychology Review 103(4): 650–669
Janssen M.C.W. (1998) Focal points. In: Newman P. (Ed.), The new palgrave of economics and the law. London, MacMillan, pp 150–155
Kahneman D., Tversky A. (1979) Prospect theory: An analysis of decision under risk. Econometrica 47: 263–291
Lin R., Kraus S., Wilkenfeld J., Barry J. (2008) Negotiating with bounded rational agents in environments with incomplete information using an automated agent. Artificial Intelligence 172 (6–7): 823–851
Maes P. (1995) Artificial life meets entertainment: lifelike autonomous agents. Commun. ACM 38(11): 108–114
Manisterski, E., Lin, R., & Kraus, S. (2008). Understanding how people design trading agents over time. In AAMAS’08 (pp. 1593–1596).
Mitchell M. T. (1997) Machine learning. McGraw-Hill, New York
Murakami, Y., Sugimoto, Y., & Ishida, T. (2005). Modeling human behavior for virtual training systems. In AAAI (pp. 127–132).
Nash J. (1951,September) Non-cooperative games. The Annals of Mathematics 54(2): 286–295
Neumann V. J., Morgenstern O. (1944) Theory of games and economic behavior. Princeton University Press, Princeton
Nilsson H., Rieskamp J., Wagenmakers E.-J. (2011) Hierarchical bayesian parameter estimation for cumulative prospect theory. Journal of Mathematical Psychology (Print) 55(1): 84–93
Ratcliff R., Smith L. P. (2004,April) A comparison of sequential sampling models for two-choice reaction time. Psychological Review 111(2): 333–367
Rosenfeld, A., Bareket, Z., Goldman, C. V., Kraus, S., LeBlanc, D. J., & Tshimoni, O. (2012). Learning drivers behavior to improve the acceptance of adaptive cruise control. In Innovative applications of artificial intelligence. AAAI.
Rosenfeld, A., & Kraus, S. (2009). Modeling agents through bounded rationality theories. In IJCAI (pp. 264–271).
Rosenfeld, A., & Kraus, S. (2011). Using aspiration adaptation theory to improve learning. In AAMAS (pp. 423-430).
Russell J. S., Norvig P. (2003) Artificial intelligence: A modern approach. Prentice Hall, Upper Saddle River
Schelling T. (1963) The strategy of conflict. Oxford University Press, New York
Selten R. (1998) Aspiration adaptation theory. Journal of Mathematical Psychology 42: 1910–214
Simon A. H. (1957) Models of man. Wiley, New York
Zuckerman I., Kraus S., Rosenschein S. J. (2011) Using focal point learning to improve human-machine tacit coordination. Autonomous Agents and Multi-Agent Systems 22(2): 289–316
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Rosenfeld, A., Zuckerman, I., Azaria, A. et al. Combining psychological models with machine learning to better predict people’s decisions. Synthese 189 (Suppl 1), 81–93 (2012). https://doi.org/10.1007/s11229-012-0182-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11229-012-0182-z