Preferential Attachment and the Search for Successful Theories.
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 so...
| Publicado en: | Philosophy of Science Vol. 80; no. 5; pp. 769 - 783 |
|---|---|
| Autor principal: | |
| Formato: | Artículo |
| Publicado: |
Cambridge University Press
Dec2013
|
| Materias: | |
| Acceso en línea: | Ver este registro en EBSCOhost |
| Sumario: | 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. |
|---|