Hostname: page-component-76fb5796d-wq484 Total loading time: 0 Render date: 2024-04-25T17:01:39.828Z Has data issue: false hasContentIssue false
  • English
  • Français

Preferential Attachment and the Search for Successful Theories

Published online by Cambridge University Press:  01 January 2022

J. McKenzie Alexander
Get access Rights & Permissions [Opens in a new window]

Abstract

Multiarm bandit problems have been used to model the selection of competing scientific theories by boundedly rational agents. In this article, I define a variable-arm bandit problem, which allows the set of scientific theories to vary over time. I show that Roth-Erev reinforcement learning, which solves multiarm bandit problems in the limit, cannot solve this problem in a reasonable time. However, social learning via preferential attachment combined with individual reinforcement learning, which discounts the past, does.

Type
General Philosophy of Science
Information
Philosophy of Science , Volume 80 , Issue 5 , December 2013 , pp. 769 - 782
Copyright
Copyright © The Philosophy of Science Association

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Alexander, J. McKenzie. Forthcoming. “Learning to Signal in a Dynamic World.” British Journal for the Philosophy of Science.Google Scholar
Alexander, J. McKenzie, Skyrms, Brian, and Zabell, Sandy. 2012. “Inventing New Signals.” Dynamic Games and Applications 2 (1): 129–45..Google Scholar
Barabási, A. L., Jeong, H., Néda, Z., Ravasz, E., Schubert, A., and Vicsek, T.. 2002. “Evolution of the Social Network of Scientific Collaborations.” Physica A 311:590–614.CrossRefGoogle Scholar
Beggs, A. 2005. “On the Convergence of Reinforcement Learning.” Journal of Economic Theory 122:1–36.CrossRefGoogle Scholar
Caplin, Andrew, and Leahy, John. 2004. “The Social Discount Rate.” Journal of Political Economy 112 (6): 1257–68..CrossRefGoogle Scholar
Hoppe, Fred M. 1984. “Pólya-like Urns and the Ewens’ Sampling Formula.” Journal of Mathematical Biology 20:91–94.CrossRefGoogle Scholar
Mill, John Stuart. 1904. A System of Logic, Ratiocinative and Inductive: Being a Connected View of the Principles of Evidence and the Methods of Scientific Investigation. 8th ed. London: Longmans.Google Scholar
Newman, Mark E. J. 2004. “Coauthorship Networks and Patterns of Scientific Collaboration.” Proceedings of the National Academy of Sciences 101:5200–5205.CrossRefGoogle ScholarPubMed
Peirce, Charles S. 1992. The Essential Peirce. Vol. 1. Bloomington: Indiana University Press.Google Scholar
Roth, Alvin E., and Erev, Ido. 1995. “Learning in Extensive Form Games: Experimental Data and Simple Dynamic Models in the Intermediate Term.” Games and Economic Behavior 8:164–212.CrossRefGoogle Scholar
Skyrms, Brian. 2010. Signals: Evolution, Learning, and Information. Oxford: Oxford University Press.CrossRefGoogle Scholar
Wagner, Caroline S., and Leydesdorff, Loet. 2005. “Network Structure, Self-Organization, and the Growth of International Collaboration in Science.” Research Policy 34:1608–18.CrossRefGoogle Scholar
Whittle, P. 1981. “Arm-Acquiring Bandits.” Annals of Probability 9 (2): 284–92..CrossRefGoogle Scholar
Wolf, Charles Jr. 1970. “The Present Value of the Past.” Journal of Political Economy 78 (4): 783–92..CrossRefGoogle Scholar
Zollman, Kevin J. S. 2007. “Network Epistemology.” PhD diss., University of California, Irvine.Google Scholar
Zollman, Kevin J. S. 2010. “The Epistemic Benefit of Transient Diversity.” Erkenntnis 72 (1): 17–35..CrossRefGoogle Scholar