Preferential attachment and the search for successful theories

Alexander, J. McKenzie ORCID: 0000-0002-2663-6993 (2013) Preferential attachment and the search for successful theories. Philosophy of Science, 80 (5). pp. 769-782. ISSN 0031-8248

Full text not available from this repository.

• Publisher

Abstract

Multiarm bandit problems have been used to model the selection of competing scientific theories by boundedly rational agents. In this paper, 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.

Item Type:	Article
Official URL:	http://www.press.uchicago.edu/ucp/journals/journal...
Additional Information:	© 2013 Philosophy of Science Association
Divisions:	Philosophy, Logic and Scientific Method
Subjects:	B Philosophy. Psychology. Religion > B Philosophy (General) Q Science > Q Science (General)
Date Deposited:	09 Aug 2012 07:29
Last Modified:	01 Nov 2024 05:23
URI:	http://eprints.lse.ac.uk/id/eprint/45283

Actions (login required)

View Item